V1.0
This commit is contained in:
parent
8fb1cbc8d2
commit
f10a9bbbc0
|
|
@ -0,0 +1,94 @@
|
|||
## Contributing to YOLOv5 🚀
|
||||
|
||||
We love your input! We want to make contributing to YOLOv5 as easy and transparent as possible, whether it's:
|
||||
|
||||
- Reporting a bug
|
||||
- Discussing the current state of the code
|
||||
- Submitting a fix
|
||||
- Proposing a new feature
|
||||
- Becoming a maintainer
|
||||
|
||||
YOLOv5 works so well due to our combined community effort, and for every small improvement you contribute you will be
|
||||
helping push the frontiers of what's possible in AI 😃!
|
||||
|
||||
## Submitting a Pull Request (PR) 🛠️
|
||||
|
||||
Submitting a PR is easy! This example shows how to submit a PR for updating `requirements.txt` in 4 steps:
|
||||
|
||||
### 1. Select File to Update
|
||||
|
||||
Select `requirements.txt` to update by clicking on it in GitHub.
|
||||
<p align="center"><img width="800" alt="PR_step1" src="https://user-images.githubusercontent.com/26833433/122260847-08be2600-ced4-11eb-828b-8287ace4136c.png"></p>
|
||||
|
||||
### 2. Click 'Edit this file'
|
||||
|
||||
Button is in top-right corner.
|
||||
<p align="center"><img width="800" alt="PR_step2" src="https://user-images.githubusercontent.com/26833433/122260844-06f46280-ced4-11eb-9eec-b8a24be519ca.png"></p>
|
||||
|
||||
### 3. Make Changes
|
||||
|
||||
Change `matplotlib` version from `3.2.2` to `3.3`.
|
||||
<p align="center"><img width="800" alt="PR_step3" src="https://user-images.githubusercontent.com/26833433/122260853-0a87e980-ced4-11eb-9fd2-3650fb6e0842.png"></p>
|
||||
|
||||
### 4. Preview Changes and Submit PR
|
||||
|
||||
Click on the **Preview changes** tab to verify your updates. At the bottom of the screen select 'Create a **new branch**
|
||||
for this commit', assign your branch a descriptive name such as `fix/matplotlib_version` and click the green **Propose
|
||||
changes** button. All done, your PR is now submitted to YOLOv5 for review and approval 😃!
|
||||
<p align="center"><img width="800" alt="PR_step4" src="https://user-images.githubusercontent.com/26833433/122260856-0b208000-ced4-11eb-8e8e-77b6151cbcc3.png"></p>
|
||||
|
||||
### PR recommendations
|
||||
|
||||
To allow your work to be integrated as seamlessly as possible, we advise you to:
|
||||
|
||||
- ✅ Verify your PR is **up-to-date with upstream/master.** If your PR is behind upstream/master an
|
||||
automatic [GitHub actions](https://github.com/ultralytics/yolov5/blob/master/.github/workflows/rebase.yml) rebase may
|
||||
be attempted by including the /rebase command in a comment body, or by running the following code, replacing 'feature'
|
||||
with the name of your local branch:
|
||||
|
||||
```bash
|
||||
git remote add upstream https://github.com/ultralytics/yolov5.git
|
||||
git fetch upstream
|
||||
git checkout feature # <----- replace 'feature' with local branch name
|
||||
git merge upstream/master
|
||||
git push -u origin -f
|
||||
```
|
||||
|
||||
- ✅ Verify all Continuous Integration (CI) **checks are passing**.
|
||||
- ✅ Reduce changes to the absolute **minimum** required for your bug fix or feature addition. _"It is not daily increase
|
||||
but daily decrease, hack away the unessential. The closer to the source, the less wastage there is."_ — Bruce Lee
|
||||
|
||||
## Submitting a Bug Report 🐛
|
||||
|
||||
If you spot a problem with YOLOv5 please submit a Bug Report!
|
||||
|
||||
For us to start investigating a possible problem we need to be able to reproduce it ourselves first. We've created a few
|
||||
short guidelines below to help users provide what we need in order to get started.
|
||||
|
||||
When asking a question, people will be better able to provide help if you provide **code** that they can easily
|
||||
understand and use to **reproduce** the problem. This is referred to by community members as creating
|
||||
a [minimum reproducible example](https://stackoverflow.com/help/minimal-reproducible-example). Your code that reproduces
|
||||
the problem should be:
|
||||
|
||||
* ✅ **Minimal** – Use as little code as possible that still produces the same problem
|
||||
* ✅ **Complete** – Provide **all** parts someone else needs to reproduce your problem in the question itself
|
||||
* ✅ **Reproducible** – Test the code you're about to provide to make sure it reproduces the problem
|
||||
|
||||
In addition to the above requirements, for [Ultralytics](https://ultralytics.com/) to provide assistance your code
|
||||
should be:
|
||||
|
||||
* ✅ **Current** – Verify that your code is up-to-date with current
|
||||
GitHub [master](https://github.com/ultralytics/yolov5/tree/master), and if necessary `git pull` or `git clone` a new
|
||||
copy to ensure your problem has not already been resolved by previous commits.
|
||||
* ✅ **Unmodified** – Your problem must be reproducible without any modifications to the codebase in this
|
||||
repository. [Ultralytics](https://ultralytics.com/) does not provide support for custom code ⚠️.
|
||||
|
||||
If you believe your problem meets all of the above criteria, please close this issue and raise a new one using the 🐛 **
|
||||
Bug Report** [template](https://github.com/ultralytics/yolov5/issues/new/choose) and providing
|
||||
a [minimum reproducible example](https://stackoverflow.com/help/minimal-reproducible-example) to help us better
|
||||
understand and diagnose your problem.
|
||||
|
||||
## License
|
||||
|
||||
By contributing, you agree that your contributions will be licensed under
|
||||
the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/)
|
||||
|
|
@ -0,0 +1,61 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Start FROM Nvidia PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch
|
||||
FROM nvcr.io/nvidia/pytorch:21.05-py3
|
||||
|
||||
# Install linux packages
|
||||
RUN apt update && apt install -y zip htop screen libgl1-mesa-glx
|
||||
|
||||
# Install python dependencies
|
||||
COPY requirements.txt .
|
||||
RUN python -m pip install --upgrade pip
|
||||
RUN pip uninstall -y nvidia-tensorboard nvidia-tensorboard-plugin-dlprof
|
||||
RUN pip install --no-cache -r requirements.txt coremltools onnx gsutil notebook wandb>=0.12.2
|
||||
RUN pip install --no-cache -U torch torchvision numpy
|
||||
# RUN pip install --no-cache torch==1.9.1+cu111 torchvision==0.10.1+cu111 -f https://download.pytorch.org/whl/torch_stable.html
|
||||
|
||||
# Create working directory
|
||||
RUN mkdir -p /usr/src/app
|
||||
WORKDIR /usr/src/app
|
||||
|
||||
# Copy contents
|
||||
COPY . /usr/src/app
|
||||
|
||||
# Downloads to user config dir
|
||||
ADD https://ultralytics.com/assets/Arial.ttf /root/.config/Ultralytics/
|
||||
|
||||
# Set environment variables
|
||||
# ENV HOME=/usr/src/app
|
||||
|
||||
|
||||
# Usage Examples -------------------------------------------------------------------------------------------------------
|
||||
|
||||
# Build and Push
|
||||
# t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t
|
||||
|
||||
# Pull and Run
|
||||
# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t
|
||||
|
||||
# Pull and Run with local directory access
|
||||
# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t
|
||||
|
||||
# Kill all
|
||||
# sudo docker kill $(sudo docker ps -q)
|
||||
|
||||
# Kill all image-based
|
||||
# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest)
|
||||
|
||||
# Bash into running container
|
||||
# sudo docker exec -it 5a9b5863d93d bash
|
||||
|
||||
# Bash into stopped container
|
||||
# id=$(sudo docker ps -qa) && sudo docker start $id && sudo docker exec -it $id bash
|
||||
|
||||
# Clean up
|
||||
# docker system prune -a --volumes
|
||||
|
||||
# Update Ubuntu drivers
|
||||
# https://www.maketecheasier.com/install-nvidia-drivers-ubuntu/
|
||||
|
||||
# DDP test
|
||||
# python -m torch.distributed.run --nproc_per_node 2 --master_port 1 train.py --epochs 3
|
||||
|
|
@ -0,0 +1,674 @@
|
|||
GNU GENERAL PUBLIC LICENSE
|
||||
Version 3, 29 June 2007
|
||||
|
||||
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
|
||||
Everyone is permitted to copy and distribute verbatim copies
|
||||
of this license document, but changing it is not allowed.
|
||||
|
||||
Preamble
|
||||
|
||||
The GNU General Public License is a free, copyleft license for
|
||||
software and other kinds of works.
|
||||
|
||||
The licenses for most software and other practical works are designed
|
||||
to take away your freedom to share and change the works. By contrast,
|
||||
the GNU General Public License is intended to guarantee your freedom to
|
||||
share and change all versions of a program--to make sure it remains free
|
||||
software for all its users. We, the Free Software Foundation, use the
|
||||
GNU General Public License for most of our software; it applies also to
|
||||
any other work released this way by its authors. You can apply it to
|
||||
your programs, too.
|
||||
|
||||
When we speak of free software, we are referring to freedom, not
|
||||
price. Our General Public Licenses are designed to make sure that you
|
||||
have the freedom to distribute copies of free software (and charge for
|
||||
them if you wish), that you receive source code or can get it if you
|
||||
want it, that you can change the software or use pieces of it in new
|
||||
free programs, and that you know you can do these things.
|
||||
|
||||
To protect your rights, we need to prevent others from denying you
|
||||
these rights or asking you to surrender the rights. Therefore, you have
|
||||
certain responsibilities if you distribute copies of the software, or if
|
||||
you modify it: responsibilities to respect the freedom of others.
|
||||
|
||||
For example, if you distribute copies of such a program, whether
|
||||
gratis or for a fee, you must pass on to the recipients the same
|
||||
freedoms that you received. You must make sure that they, too, receive
|
||||
or can get the source code. And you must show them these terms so they
|
||||
know their rights.
|
||||
|
||||
Developers that use the GNU GPL protect your rights with two steps:
|
||||
(1) assert copyright on the software, and (2) offer you this License
|
||||
giving you legal permission to copy, distribute and/or modify it.
|
||||
|
||||
For the developers' and authors' protection, the GPL clearly explains
|
||||
that there is no warranty for this free software. For both users' and
|
||||
authors' sake, the GPL requires that modified versions be marked as
|
||||
changed, so that their problems will not be attributed erroneously to
|
||||
authors of previous versions.
|
||||
|
||||
Some devices are designed to deny users access to install or run
|
||||
modified versions of the software inside them, although the manufacturer
|
||||
can do so. This is fundamentally incompatible with the aim of
|
||||
protecting users' freedom to change the software. The systematic
|
||||
pattern of such abuse occurs in the area of products for individuals to
|
||||
use, which is precisely where it is most unacceptable. Therefore, we
|
||||
have designed this version of the GPL to prohibit the practice for those
|
||||
products. If such problems arise substantially in other domains, we
|
||||
stand ready to extend this provision to those domains in future versions
|
||||
of the GPL, as needed to protect the freedom of users.
|
||||
|
||||
Finally, every program is threatened constantly by software patents.
|
||||
States should not allow patents to restrict development and use of
|
||||
software on general-purpose computers, but in those that do, we wish to
|
||||
avoid the special danger that patents applied to a free program could
|
||||
make it effectively proprietary. To prevent this, the GPL assures that
|
||||
patents cannot be used to render the program non-free.
|
||||
|
||||
The precise terms and conditions for copying, distribution and
|
||||
modification follow.
|
||||
|
||||
TERMS AND CONDITIONS
|
||||
|
||||
0. Definitions.
|
||||
|
||||
"This License" refers to version 3 of the GNU General Public License.
|
||||
|
||||
"Copyright" also means copyright-like laws that apply to other kinds of
|
||||
works, such as semiconductor masks.
|
||||
|
||||
"The Program" refers to any copyrightable work licensed under this
|
||||
License. Each licensee is addressed as "you". "Licensees" and
|
||||
"recipients" may be individuals or organizations.
|
||||
|
||||
To "modify" a work means to copy from or adapt all or part of the work
|
||||
in a fashion requiring copyright permission, other than the making of an
|
||||
exact copy. The resulting work is called a "modified version" of the
|
||||
earlier work or a work "based on" the earlier work.
|
||||
|
||||
A "covered work" means either the unmodified Program or a work based
|
||||
on the Program.
|
||||
|
||||
To "propagate" a work means to do anything with it that, without
|
||||
permission, would make you directly or secondarily liable for
|
||||
infringement under applicable copyright law, except executing it on a
|
||||
computer or modifying a private copy. Propagation includes copying,
|
||||
distribution (with or without modification), making available to the
|
||||
public, and in some countries other activities as well.
|
||||
|
||||
To "convey" a work means any kind of propagation that enables other
|
||||
parties to make or receive copies. Mere interaction with a user through
|
||||
a computer network, with no transfer of a copy, is not conveying.
|
||||
|
||||
An interactive user interface displays "Appropriate Legal Notices"
|
||||
to the extent that it includes a convenient and prominently visible
|
||||
feature that (1) displays an appropriate copyright notice, and (2)
|
||||
tells the user that there is no warranty for the work (except to the
|
||||
extent that warranties are provided), that licensees may convey the
|
||||
work under this License, and how to view a copy of this License. If
|
||||
the interface presents a list of user commands or options, such as a
|
||||
menu, a prominent item in the list meets this criterion.
|
||||
|
||||
1. Source Code.
|
||||
|
||||
The "source code" for a work means the preferred form of the work
|
||||
for making modifications to it. "Object code" means any non-source
|
||||
form of a work.
|
||||
|
||||
A "Standard Interface" means an interface that either is an official
|
||||
standard defined by a recognized standards body, or, in the case of
|
||||
interfaces specified for a particular programming language, one that
|
||||
is widely used among developers working in that language.
|
||||
|
||||
The "System Libraries" of an executable work include anything, other
|
||||
than the work as a whole, that (a) is included in the normal form of
|
||||
packaging a Major Component, but which is not part of that Major
|
||||
Component, and (b) serves only to enable use of the work with that
|
||||
Major Component, or to implement a Standard Interface for which an
|
||||
implementation is available to the public in source code form. A
|
||||
"Major Component", in this context, means a major essential component
|
||||
(kernel, window system, and so on) of the specific operating system
|
||||
(if any) on which the executable work runs, or a compiler used to
|
||||
produce the work, or an object code interpreter used to run it.
|
||||
|
||||
The "Corresponding Source" for a work in object code form means all
|
||||
the source code needed to generate, install, and (for an executable
|
||||
work) run the object code and to modify the work, including scripts to
|
||||
control those activities. However, it does not include the work's
|
||||
System Libraries, or general-purpose tools or generally available free
|
||||
programs which are used unmodified in performing those activities but
|
||||
which are not part of the work. For example, Corresponding Source
|
||||
includes interface definition files associated with source files for
|
||||
the work, and the source code for shared libraries and dynamically
|
||||
linked subprograms that the work is specifically designed to require,
|
||||
such as by intimate data communication or control flow between those
|
||||
subprograms and other parts of the work.
|
||||
|
||||
The Corresponding Source need not include anything that users
|
||||
can regenerate automatically from other parts of the Corresponding
|
||||
Source.
|
||||
|
||||
The Corresponding Source for a work in source code form is that
|
||||
same work.
|
||||
|
||||
2. Basic Permissions.
|
||||
|
||||
All rights granted under this License are granted for the term of
|
||||
copyright on the Program, and are irrevocable provided the stated
|
||||
conditions are met. This License explicitly affirms your unlimited
|
||||
permission to run the unmodified Program. The output from running a
|
||||
covered work is covered by this License only if the output, given its
|
||||
content, constitutes a covered work. This License acknowledges your
|
||||
rights of fair use or other equivalent, as provided by copyright law.
|
||||
|
||||
You may make, run and propagate covered works that you do not
|
||||
convey, without conditions so long as your license otherwise remains
|
||||
in force. You may convey covered works to others for the sole purpose
|
||||
of having them make modifications exclusively for you, or provide you
|
||||
with facilities for running those works, provided that you comply with
|
||||
the terms of this License in conveying all material for which you do
|
||||
not control copyright. Those thus making or running the covered works
|
||||
for you must do so exclusively on your behalf, under your direction
|
||||
and control, on terms that prohibit them from making any copies of
|
||||
your copyrighted material outside their relationship with you.
|
||||
|
||||
Conveying under any other circumstances is permitted solely under
|
||||
the conditions stated below. Sublicensing is not allowed; section 10
|
||||
makes it unnecessary.
|
||||
|
||||
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
|
||||
|
||||
No covered work shall be deemed part of an effective technological
|
||||
measure under any applicable law fulfilling obligations under article
|
||||
11 of the WIPO copyright treaty adopted on 20 December 1996, or
|
||||
similar laws prohibiting or restricting circumvention of such
|
||||
measures.
|
||||
|
||||
When you convey a covered work, you waive any legal power to forbid
|
||||
circumvention of technological measures to the extent such circumvention
|
||||
is effected by exercising rights under this License with respect to
|
||||
the covered work, and you disclaim any intention to limit operation or
|
||||
modification of the work as a means of enforcing, against the work's
|
||||
users, your or third parties' legal rights to forbid circumvention of
|
||||
technological measures.
|
||||
|
||||
4. Conveying Verbatim Copies.
|
||||
|
||||
You may convey verbatim copies of the Program's source code as you
|
||||
receive it, in any medium, provided that you conspicuously and
|
||||
appropriately publish on each copy an appropriate copyright notice;
|
||||
keep intact all notices stating that this License and any
|
||||
non-permissive terms added in accord with section 7 apply to the code;
|
||||
keep intact all notices of the absence of any warranty; and give all
|
||||
recipients a copy of this License along with the Program.
|
||||
|
||||
You may charge any price or no price for each copy that you convey,
|
||||
and you may offer support or warranty protection for a fee.
|
||||
|
||||
5. Conveying Modified Source Versions.
|
||||
|
||||
You may convey a work based on the Program, or the modifications to
|
||||
produce it from the Program, in the form of source code under the
|
||||
terms of section 4, provided that you also meet all of these conditions:
|
||||
|
||||
a) The work must carry prominent notices stating that you modified
|
||||
it, and giving a relevant date.
|
||||
|
||||
b) The work must carry prominent notices stating that it is
|
||||
released under this License and any conditions added under section
|
||||
7. This requirement modifies the requirement in section 4 to
|
||||
"keep intact all notices".
|
||||
|
||||
c) You must license the entire work, as a whole, under this
|
||||
License to anyone who comes into possession of a copy. This
|
||||
License will therefore apply, along with any applicable section 7
|
||||
additional terms, to the whole of the work, and all its parts,
|
||||
regardless of how they are packaged. This License gives no
|
||||
permission to license the work in any other way, but it does not
|
||||
invalidate such permission if you have separately received it.
|
||||
|
||||
d) If the work has interactive user interfaces, each must display
|
||||
Appropriate Legal Notices; however, if the Program has interactive
|
||||
interfaces that do not display Appropriate Legal Notices, your
|
||||
work need not make them do so.
|
||||
|
||||
A compilation of a covered work with other separate and independent
|
||||
works, which are not by their nature extensions of the covered work,
|
||||
and which are not combined with it such as to form a larger program,
|
||||
in or on a volume of a storage or distribution medium, is called an
|
||||
"aggregate" if the compilation and its resulting copyright are not
|
||||
used to limit the access or legal rights of the compilation's users
|
||||
beyond what the individual works permit. Inclusion of a covered work
|
||||
in an aggregate does not cause this License to apply to the other
|
||||
parts of the aggregate.
|
||||
|
||||
6. Conveying Non-Source Forms.
|
||||
|
||||
You may convey a covered work in object code form under the terms
|
||||
of sections 4 and 5, provided that you also convey the
|
||||
machine-readable Corresponding Source under the terms of this License,
|
||||
in one of these ways:
|
||||
|
||||
a) Convey the object code in, or embodied in, a physical product
|
||||
(including a physical distribution medium), accompanied by the
|
||||
Corresponding Source fixed on a durable physical medium
|
||||
customarily used for software interchange.
|
||||
|
||||
b) Convey the object code in, or embodied in, a physical product
|
||||
(including a physical distribution medium), accompanied by a
|
||||
written offer, valid for at least three years and valid for as
|
||||
long as you offer spare parts or customer support for that product
|
||||
model, to give anyone who possesses the object code either (1) a
|
||||
copy of the Corresponding Source for all the software in the
|
||||
product that is covered by this License, on a durable physical
|
||||
medium customarily used for software interchange, for a price no
|
||||
more than your reasonable cost of physically performing this
|
||||
conveying of source, or (2) access to copy the
|
||||
Corresponding Source from a network server at no charge.
|
||||
|
||||
c) Convey individual copies of the object code with a copy of the
|
||||
written offer to provide the Corresponding Source. This
|
||||
alternative is allowed only occasionally and noncommercially, and
|
||||
only if you received the object code with such an offer, in accord
|
||||
with subsection 6b.
|
||||
|
||||
d) Convey the object code by offering access from a designated
|
||||
place (gratis or for a charge), and offer equivalent access to the
|
||||
Corresponding Source in the same way through the same place at no
|
||||
further charge. You need not require recipients to copy the
|
||||
Corresponding Source along with the object code. If the place to
|
||||
copy the object code is a network server, the Corresponding Source
|
||||
may be on a different server (operated by you or a third party)
|
||||
that supports equivalent copying facilities, provided you maintain
|
||||
clear directions next to the object code saying where to find the
|
||||
Corresponding Source. Regardless of what server hosts the
|
||||
Corresponding Source, you remain obligated to ensure that it is
|
||||
available for as long as needed to satisfy these requirements.
|
||||
|
||||
e) Convey the object code using peer-to-peer transmission, provided
|
||||
you inform other peers where the object code and Corresponding
|
||||
Source of the work are being offered to the general public at no
|
||||
charge under subsection 6d.
|
||||
|
||||
A separable portion of the object code, whose source code is excluded
|
||||
from the Corresponding Source as a System Library, need not be
|
||||
included in conveying the object code work.
|
||||
|
||||
A "User Product" is either (1) a "consumer product", which means any
|
||||
tangible personal property which is normally used for personal, family,
|
||||
or household purposes, or (2) anything designed or sold for incorporation
|
||||
into a dwelling. In determining whether a product is a consumer product,
|
||||
doubtful cases shall be resolved in favor of coverage. For a particular
|
||||
product received by a particular user, "normally used" refers to a
|
||||
typical or common use of that class of product, regardless of the status
|
||||
of the particular user or of the way in which the particular user
|
||||
actually uses, or expects or is expected to use, the product. A product
|
||||
is a consumer product regardless of whether the product has substantial
|
||||
commercial, industrial or non-consumer uses, unless such uses represent
|
||||
the only significant mode of use of the product.
|
||||
|
||||
"Installation Information" for a User Product means any methods,
|
||||
procedures, authorization keys, or other information required to install
|
||||
and execute modified versions of a covered work in that User Product from
|
||||
a modified version of its Corresponding Source. The information must
|
||||
suffice to ensure that the continued functioning of the modified object
|
||||
code is in no case prevented or interfered with solely because
|
||||
modification has been made.
|
||||
|
||||
If you convey an object code work under this section in, or with, or
|
||||
specifically for use in, a User Product, and the conveying occurs as
|
||||
part of a transaction in which the right of possession and use of the
|
||||
User Product is transferred to the recipient in perpetuity or for a
|
||||
fixed term (regardless of how the transaction is characterized), the
|
||||
Corresponding Source conveyed under this section must be accompanied
|
||||
by the Installation Information. But this requirement does not apply
|
||||
if neither you nor any third party retains the ability to install
|
||||
modified object code on the User Product (for example, the work has
|
||||
been installed in ROM).
|
||||
|
||||
The requirement to provide Installation Information does not include a
|
||||
requirement to continue to provide support service, warranty, or updates
|
||||
for a work that has been modified or installed by the recipient, or for
|
||||
the User Product in which it has been modified or installed. Access to a
|
||||
network may be denied when the modification itself materially and
|
||||
adversely affects the operation of the network or violates the rules and
|
||||
protocols for communication across the network.
|
||||
|
||||
Corresponding Source conveyed, and Installation Information provided,
|
||||
in accord with this section must be in a format that is publicly
|
||||
documented (and with an implementation available to the public in
|
||||
source code form), and must require no special password or key for
|
||||
unpacking, reading or copying.
|
||||
|
||||
7. Additional Terms.
|
||||
|
||||
"Additional permissions" are terms that supplement the terms of this
|
||||
License by making exceptions from one or more of its conditions.
|
||||
Additional permissions that are applicable to the entire Program shall
|
||||
be treated as though they were included in this License, to the extent
|
||||
that they are valid under applicable law. If additional permissions
|
||||
apply only to part of the Program, that part may be used separately
|
||||
under those permissions, but the entire Program remains governed by
|
||||
this License without regard to the additional permissions.
|
||||
|
||||
When you convey a copy of a covered work, you may at your option
|
||||
remove any additional permissions from that copy, or from any part of
|
||||
it. (Additional permissions may be written to require their own
|
||||
removal in certain cases when you modify the work.) You may place
|
||||
additional permissions on material, added by you to a covered work,
|
||||
for which you have or can give appropriate copyright permission.
|
||||
|
||||
Notwithstanding any other provision of this License, for material you
|
||||
add to a covered work, you may (if authorized by the copyright holders of
|
||||
that material) supplement the terms of this License with terms:
|
||||
|
||||
a) Disclaiming warranty or limiting liability differently from the
|
||||
terms of sections 15 and 16 of this License; or
|
||||
|
||||
b) Requiring preservation of specified reasonable legal notices or
|
||||
author attributions in that material or in the Appropriate Legal
|
||||
Notices displayed by works containing it; or
|
||||
|
||||
c) Prohibiting misrepresentation of the origin of that material, or
|
||||
requiring that modified versions of such material be marked in
|
||||
reasonable ways as different from the original version; or
|
||||
|
||||
d) Limiting the use for publicity purposes of names of licensors or
|
||||
authors of the material; or
|
||||
|
||||
e) Declining to grant rights under trademark law for use of some
|
||||
trade names, trademarks, or service marks; or
|
||||
|
||||
f) Requiring indemnification of licensors and authors of that
|
||||
material by anyone who conveys the material (or modified versions of
|
||||
it) with contractual assumptions of liability to the recipient, for
|
||||
any liability that these contractual assumptions directly impose on
|
||||
those licensors and authors.
|
||||
|
||||
All other non-permissive additional terms are considered "further
|
||||
restrictions" within the meaning of section 10. If the Program as you
|
||||
received it, or any part of it, contains a notice stating that it is
|
||||
governed by this License along with a term that is a further
|
||||
restriction, you may remove that term. If a license document contains
|
||||
a further restriction but permits relicensing or conveying under this
|
||||
License, you may add to a covered work material governed by the terms
|
||||
of that license document, provided that the further restriction does
|
||||
not survive such relicensing or conveying.
|
||||
|
||||
If you add terms to a covered work in accord with this section, you
|
||||
must place, in the relevant source files, a statement of the
|
||||
additional terms that apply to those files, or a notice indicating
|
||||
where to find the applicable terms.
|
||||
|
||||
Additional terms, permissive or non-permissive, may be stated in the
|
||||
form of a separately written license, or stated as exceptions;
|
||||
the above requirements apply either way.
|
||||
|
||||
8. Termination.
|
||||
|
||||
You may not propagate or modify a covered work except as expressly
|
||||
provided under this License. Any attempt otherwise to propagate or
|
||||
modify it is void, and will automatically terminate your rights under
|
||||
this License (including any patent licenses granted under the third
|
||||
paragraph of section 11).
|
||||
|
||||
However, if you cease all violation of this License, then your
|
||||
license from a particular copyright holder is reinstated (a)
|
||||
provisionally, unless and until the copyright holder explicitly and
|
||||
finally terminates your license, and (b) permanently, if the copyright
|
||||
holder fails to notify you of the violation by some reasonable means
|
||||
prior to 60 days after the cessation.
|
||||
|
||||
Moreover, your license from a particular copyright holder is
|
||||
reinstated permanently if the copyright holder notifies you of the
|
||||
violation by some reasonable means, this is the first time you have
|
||||
received notice of violation of this License (for any work) from that
|
||||
copyright holder, and you cure the violation prior to 30 days after
|
||||
your receipt of the notice.
|
||||
|
||||
Termination of your rights under this section does not terminate the
|
||||
licenses of parties who have received copies or rights from you under
|
||||
this License. If your rights have been terminated and not permanently
|
||||
reinstated, you do not qualify to receive new licenses for the same
|
||||
material under section 10.
|
||||
|
||||
9. Acceptance Not Required for Having Copies.
|
||||
|
||||
You are not required to accept this License in order to receive or
|
||||
run a copy of the Program. Ancillary propagation of a covered work
|
||||
occurring solely as a consequence of using peer-to-peer transmission
|
||||
to receive a copy likewise does not require acceptance. However,
|
||||
nothing other than this License grants you permission to propagate or
|
||||
modify any covered work. These actions infringe copyright if you do
|
||||
not accept this License. Therefore, by modifying or propagating a
|
||||
covered work, you indicate your acceptance of this License to do so.
|
||||
|
||||
10. Automatic Licensing of Downstream Recipients.
|
||||
|
||||
Each time you convey a covered work, the recipient automatically
|
||||
receives a license from the original licensors, to run, modify and
|
||||
propagate that work, subject to this License. You are not responsible
|
||||
for enforcing compliance by third parties with this License.
|
||||
|
||||
An "entity transaction" is a transaction transferring control of an
|
||||
organization, or substantially all assets of one, or subdividing an
|
||||
organization, or merging organizations. If propagation of a covered
|
||||
work results from an entity transaction, each party to that
|
||||
transaction who receives a copy of the work also receives whatever
|
||||
licenses to the work the party's predecessor in interest had or could
|
||||
give under the previous paragraph, plus a right to possession of the
|
||||
Corresponding Source of the work from the predecessor in interest, if
|
||||
the predecessor has it or can get it with reasonable efforts.
|
||||
|
||||
You may not impose any further restrictions on the exercise of the
|
||||
rights granted or affirmed under this License. For example, you may
|
||||
not impose a license fee, royalty, or other charge for exercise of
|
||||
rights granted under this License, and you may not initiate litigation
|
||||
(including a cross-claim or counterclaim in a lawsuit) alleging that
|
||||
any patent claim is infringed by making, using, selling, offering for
|
||||
sale, or importing the Program or any portion of it.
|
||||
|
||||
11. Patents.
|
||||
|
||||
A "contributor" is a copyright holder who authorizes use under this
|
||||
License of the Program or a work on which the Program is based. The
|
||||
work thus licensed is called the contributor's "contributor version".
|
||||
|
||||
A contributor's "essential patent claims" are all patent claims
|
||||
owned or controlled by the contributor, whether already acquired or
|
||||
hereafter acquired, that would be infringed by some manner, permitted
|
||||
by this License, of making, using, or selling its contributor version,
|
||||
but do not include claims that would be infringed only as a
|
||||
consequence of further modification of the contributor version. For
|
||||
purposes of this definition, "control" includes the right to grant
|
||||
patent sublicenses in a manner consistent with the requirements of
|
||||
this License.
|
||||
|
||||
Each contributor grants you a non-exclusive, worldwide, royalty-free
|
||||
patent license under the contributor's essential patent claims, to
|
||||
make, use, sell, offer for sale, import and otherwise run, modify and
|
||||
propagate the contents of its contributor version.
|
||||
|
||||
In the following three paragraphs, a "patent license" is any express
|
||||
agreement or commitment, however denominated, not to enforce a patent
|
||||
(such as an express permission to practice a patent or covenant not to
|
||||
sue for patent infringement). To "grant" such a patent license to a
|
||||
party means to make such an agreement or commitment not to enforce a
|
||||
patent against the party.
|
||||
|
||||
If you convey a covered work, knowingly relying on a patent license,
|
||||
and the Corresponding Source of the work is not available for anyone
|
||||
to copy, free of charge and under the terms of this License, through a
|
||||
publicly available network server or other readily accessible means,
|
||||
then you must either (1) cause the Corresponding Source to be so
|
||||
available, or (2) arrange to deprive yourself of the benefit of the
|
||||
patent license for this particular work, or (3) arrange, in a manner
|
||||
consistent with the requirements of this License, to extend the patent
|
||||
license to downstream recipients. "Knowingly relying" means you have
|
||||
actual knowledge that, but for the patent license, your conveying the
|
||||
covered work in a country, or your recipient's use of the covered work
|
||||
in a country, would infringe one or more identifiable patents in that
|
||||
country that you have reason to believe are valid.
|
||||
|
||||
If, pursuant to or in connection with a single transaction or
|
||||
arrangement, you convey, or propagate by procuring conveyance of, a
|
||||
covered work, and grant a patent license to some of the parties
|
||||
receiving the covered work authorizing them to use, propagate, modify
|
||||
or convey a specific copy of the covered work, then the patent license
|
||||
you grant is automatically extended to all recipients of the covered
|
||||
work and works based on it.
|
||||
|
||||
A patent license is "discriminatory" if it does not include within
|
||||
the scope of its coverage, prohibits the exercise of, or is
|
||||
conditioned on the non-exercise of one or more of the rights that are
|
||||
specifically granted under this License. You may not convey a covered
|
||||
work if you are a party to an arrangement with a third party that is
|
||||
in the business of distributing software, under which you make payment
|
||||
to the third party based on the extent of your activity of conveying
|
||||
the work, and under which the third party grants, to any of the
|
||||
parties who would receive the covered work from you, a discriminatory
|
||||
patent license (a) in connection with copies of the covered work
|
||||
conveyed by you (or copies made from those copies), or (b) primarily
|
||||
for and in connection with specific products or compilations that
|
||||
contain the covered work, unless you entered into that arrangement,
|
||||
or that patent license was granted, prior to 28 March 2007.
|
||||
|
||||
Nothing in this License shall be construed as excluding or limiting
|
||||
any implied license or other defenses to infringement that may
|
||||
otherwise be available to you under applicable patent law.
|
||||
|
||||
12. No Surrender of Others' Freedom.
|
||||
|
||||
If conditions are imposed on you (whether by court order, agreement or
|
||||
otherwise) that contradict the conditions of this License, they do not
|
||||
excuse you from the conditions of this License. If you cannot convey a
|
||||
covered work so as to satisfy simultaneously your obligations under this
|
||||
License and any other pertinent obligations, then as a consequence you may
|
||||
not convey it at all. For example, if you agree to terms that obligate you
|
||||
to collect a royalty for further conveying from those to whom you convey
|
||||
the Program, the only way you could satisfy both those terms and this
|
||||
License would be to refrain entirely from conveying the Program.
|
||||
|
||||
13. Use with the GNU Affero General Public License.
|
||||
|
||||
Notwithstanding any other provision of this License, you have
|
||||
permission to link or combine any covered work with a work licensed
|
||||
under version 3 of the GNU Affero General Public License into a single
|
||||
combined work, and to convey the resulting work. The terms of this
|
||||
License will continue to apply to the part which is the covered work,
|
||||
but the special requirements of the GNU Affero General Public License,
|
||||
section 13, concerning interaction through a network will apply to the
|
||||
combination as such.
|
||||
|
||||
14. Revised Versions of this License.
|
||||
|
||||
The Free Software Foundation may publish revised and/or new versions of
|
||||
the GNU General Public License from time to time. Such new versions will
|
||||
be similar in spirit to the present version, but may differ in detail to
|
||||
address new problems or concerns.
|
||||
|
||||
Each version is given a distinguishing version number. If the
|
||||
Program specifies that a certain numbered version of the GNU General
|
||||
Public License "or any later version" applies to it, you have the
|
||||
option of following the terms and conditions either of that numbered
|
||||
version or of any later version published by the Free Software
|
||||
Foundation. If the Program does not specify a version number of the
|
||||
GNU General Public License, you may choose any version ever published
|
||||
by the Free Software Foundation.
|
||||
|
||||
If the Program specifies that a proxy can decide which future
|
||||
versions of the GNU General Public License can be used, that proxy's
|
||||
public statement of acceptance of a version permanently authorizes you
|
||||
to choose that version for the Program.
|
||||
|
||||
Later license versions may give you additional or different
|
||||
permissions. However, no additional obligations are imposed on any
|
||||
author or copyright holder as a result of your choosing to follow a
|
||||
later version.
|
||||
|
||||
15. Disclaimer of Warranty.
|
||||
|
||||
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
|
||||
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
|
||||
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
|
||||
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
|
||||
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
|
||||
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
|
||||
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
|
||||
|
||||
16. Limitation of Liability.
|
||||
|
||||
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
|
||||
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
|
||||
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
|
||||
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
|
||||
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
|
||||
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
|
||||
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
|
||||
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
|
||||
SUCH DAMAGES.
|
||||
|
||||
17. Interpretation of Sections 15 and 16.
|
||||
|
||||
If the disclaimer of warranty and limitation of liability provided
|
||||
above cannot be given local legal effect according to their terms,
|
||||
reviewing courts shall apply local law that most closely approximates
|
||||
an absolute waiver of all civil liability in connection with the
|
||||
Program, unless a warranty or assumption of liability accompanies a
|
||||
copy of the Program in return for a fee.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
How to Apply These Terms to Your New Programs
|
||||
|
||||
If you develop a new program, and you want it to be of the greatest
|
||||
possible use to the public, the best way to achieve this is to make it
|
||||
free software which everyone can redistribute and change under these terms.
|
||||
|
||||
To do so, attach the following notices to the program. It is safest
|
||||
to attach them to the start of each source file to most effectively
|
||||
state the exclusion of warranty; and each file should have at least
|
||||
the "copyright" line and a pointer to where the full notice is found.
|
||||
|
||||
<one line to give the program's name and a brief idea of what it does.>
|
||||
Copyright (C) <year> <name of author>
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation, either version 3 of the License, or
|
||||
(at your option) any later version.
|
||||
|
||||
This program is distributed in the hope that it will be useful,
|
||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
GNU General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU General Public License
|
||||
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
Also add information on how to contact you by electronic and paper mail.
|
||||
|
||||
If the program does terminal interaction, make it output a short
|
||||
notice like this when it starts in an interactive mode:
|
||||
|
||||
<program> Copyright (C) <year> <name of author>
|
||||
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
|
||||
This is free software, and you are welcome to redistribute it
|
||||
under certain conditions; type `show c' for details.
|
||||
|
||||
The hypothetical commands `show w' and `show c' should show the appropriate
|
||||
parts of the General Public License. Of course, your program's commands
|
||||
might be different; for a GUI interface, you would use an "about box".
|
||||
|
||||
You should also get your employer (if you work as a programmer) or school,
|
||||
if any, to sign a "copyright disclaimer" for the program, if necessary.
|
||||
For more information on this, and how to apply and follow the GNU GPL, see
|
||||
<http://www.gnu.org/licenses/>.
|
||||
|
||||
The GNU General Public License does not permit incorporating your program
|
||||
into proprietary programs. If your program is a subroutine library, you
|
||||
may consider it more useful to permit linking proprietary applications with
|
||||
the library. If this is what you want to do, use the GNU Lesser General
|
||||
Public License instead of this License. But first, please read
|
||||
<http://www.gnu.org/philosophy/why-not-lgpl.html>.
|
||||
90
README.md
90
README.md
|
|
@ -1,3 +1,89 @@
|
|||
# Tph-Yolov5
|
||||
# TPH-YOLOv5
|
||||
This repo is the implementation of ["TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios"](https://openaccess.thecvf.com/content/ICCV2021W/VisDrone/html/Zhu_TPH-YOLOv5_Improved_YOLOv5_Based_on_Transformer_Prediction_Head_for_Object_ICCVW_2021_paper.html) and ["TPH-YOLOv5++: Boosting Object Detection on Drone-Captured Scenarios with Cross-Layer Asymmetric Transformer"](https://www.mdpi.com/2072-4292/15/6/1687).
|
||||
On [VisDrone Challenge 2021](http://aiskyeye.com/), TPH-YOLOv5 wins 4th place and achieves well-matched results with 1st place model.
|
||||
|
||||
You can get [VisDrone-DET2021: The Vision Meets Drone Object Detection Challenge Results](https://openaccess.thecvf.com/content/ICCV2021W/VisDrone/html/Cao_VisDrone-DET2021_The_Vision_Meets_Drone_Object_Detection_Challenge_Results_ICCVW_2021_paper.html) for more information. The TPH-YOLOv5++, as an improved version, significantly improves inference efficiency and reduces computational costs while maintaining detection performance compared to TPH-YOLOv5.
|
||||
|
||||
无人机视角的行人小目标检测
|
||||
# Install
|
||||
```bash
|
||||
$ git clone https://github.com/cv516Buaa/tph-yolov5
|
||||
$ cd tph-yolov5
|
||||
$ pip install -r requirements.txt
|
||||
```
|
||||
# Convert labels
|
||||
VisDrone2YOLO_lable.py transfer VisDrone annotiations to yolo labels.
|
||||
You should set the path of VisDrone dataset in VisDrone2YOLO_lable.py first.
|
||||
```bash
|
||||
$ python VisDrone2YOLO_lable.py
|
||||
```
|
||||
|
||||
# Inference
|
||||
* `Datasets` : [VisDrone](http://aiskyeye.com/download/object-detection-2/), [UAVDT](https://sites.google.com/view/grli-uavdt/%E9%A6%96%E9%A1%B5)
|
||||
* `Weights` (PyTorch
|
||||
v1.10):
|
||||
* `yolov5l-xs-1.pt`: | [Baidu Drive(pw: vibe)](https://pan.baidu.com/s/1APETgMoeCOvZi1GsBZERrg). | [Google Drive](https://drive.google.com/file/d/1nGeKl3qOa26v3haGSDmLjeA0cjDD9p61/view?usp=sharing) |
|
||||
* `yolov5l-xs-2.pt`: | [Baidu Drive(pw: vffz)](https://pan.baidu.com/s/19S84EevP86yJIvnv9KYXDA). | [Google Drive](https://drive.google.com/file/d/1VmORvxNtvMVMvmY7cCwvp0BoL6L3RGiq/view?usp=sharing) |
|
||||
|
||||
val.py runs inference on VisDrone2019-DET-val, using weights trained with TPH-YOLOv5.
|
||||
(We provide two weights trained by two different models based on YOLOv5l.)
|
||||
|
||||
```bash
|
||||
$ python val.py --weights ./weights/yolov5l-xs-1.pt --img 1996 --data ./data/VisDrone.yaml
|
||||
yolov5l-xs-2.pt
|
||||
--augment --save-txt --save-conf --task val --batch-size 8 --verbose --name v5l-xs
|
||||
```
|
||||
|
||||
Inference on UAVDT is similar and results of TPH-YOLOv5++ on UAVDT are as follow:
|
||||
|
||||
|
||||
# Ensemble
|
||||
If you inference dataset with different models, then you can ensemble the result by weighted boxes fusion using wbf.py.
|
||||
You should set img path and txt path in wbf.py.
|
||||
```bash
|
||||
$ python wbf.py
|
||||
```
|
||||
|
||||
# Train
|
||||
train.py allows you to train new model from strach.
|
||||
```bash
|
||||
$ python train.py --img 1536 --adam --batch 4 --epochs 80 --data ./data/VisDrone.yaml --weights yolov5l.pt --hy data/hyps/hyp.VisDrone.yaml --cfg models/yolov5l-xs-tph.yaml --name v5l-xs-tph
|
||||
$ python train.py --img 1536 --adam --batch 4 --epochs 80 --data ./data/VisDrone.yaml --weights yolov5l.pt --hy data/hyps/hyp.VisDrone.yaml --cfg models/yolov5l-tph-plus.yaml --name v5l-tph-plus
|
||||
```
|
||||
|
||||
|
||||
# Description of TPH-YOLOv5, TPH-YOLOv5++ and citations
|
||||
- https://arxiv.org/abs/2108.11539
|
||||
- https://openaccess.thecvf.com/content/ICCV2021W/VisDrone/html/Zhu_TPH-YOLOv5_Improved_YOLOv5_Based_on_Transformer_Prediction_Head_for_Object_ICCVW_2021_paper.html
|
||||
- https://www.mdpi.com/2072-4292/15/6/1687
|
||||
|
||||
If you have any question, please discuss with me by sending email to lyushuchang@buaa.edu.cn or liubinghao@buaa.edu.cn
|
||||
If you find this code useful please cite:
|
||||
```
|
||||
@InProceedings{Zhu_2021_ICCV,
|
||||
author = {Zhu, Xingkui and Lyu, Shuchang and Wang, Xu and Zhao, Qi},
|
||||
title = {TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios},
|
||||
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
|
||||
month = {October},
|
||||
year = {2021},
|
||||
pages = {2778-2788}
|
||||
}
|
||||
|
||||
@Article{rs15061687,
|
||||
AUTHOR = {Zhao, Qi and Liu, Binghao and Lyu, Shuchang and Wang, Chunlei and Zhang, Hong},
|
||||
TITLE = {TPH-YOLOv5++: Boosting Object Detection on Drone-Captured Scenarios with Cross-Layer Asymmetric Transformer},
|
||||
JOURNAL = {Remote Sensing},
|
||||
VOLUME = {15},
|
||||
YEAR = {2023},
|
||||
NUMBER = {6},
|
||||
ARTICLE-NUMBER = {1687},
|
||||
URL = {https://www.mdpi.com/2072-4292/15/6/1687},
|
||||
ISSN = {2072-4292},
|
||||
DOI = {10.3390/rs15061687}
|
||||
}
|
||||
```
|
||||
|
||||
# References
|
||||
Thanks to their great works
|
||||
* [ultralytics/yolov5](https://github.com/ultralytics/yolov5)
|
||||
* [SwinTransformer](https://github.com/microsoft/Swin-Transformer)
|
||||
* [WBF](https://github.com/ZFTurbo/Weighted-Boxes-Fusion)
|
||||
|
|
|
|||
|
|
@ -0,0 +1,40 @@
|
|||
import os
|
||||
import pandas as pd
|
||||
from PIL import Image
|
||||
|
||||
YOLO_LABELS_PATH = "../datasets/VisDrone/VisDrone2019-DET-val/labels"
|
||||
VISANN_PATH = "../datasets/VisDrone/VisDrone2019-DET-val/annotations/"
|
||||
VISIMG_PATH = "../datasets//VisDrone/VisDrone2019-DET-val/images/"
|
||||
|
||||
def convert(bbox, img_size):
|
||||
#将标注visDrone数据集标注转为yolov5
|
||||
#bbox top_left_x top_left_y width height
|
||||
dw = 1/(img_size[0])
|
||||
dh = 1/(img_size[1])
|
||||
x = bbox[0] + bbox[2]/2
|
||||
y = bbox[1] + bbox[3]/2
|
||||
x = x * dw
|
||||
y = y * dh
|
||||
w = bbox[2] * dw
|
||||
h = bbox[3] * dh
|
||||
return (x,y,w,h)
|
||||
|
||||
def ChangeToYolo5():
|
||||
if not os.path.exists(YOLO_LABELS_PATH):
|
||||
os.makedirs(YOLO_LABELS_PATH)
|
||||
print(len(os.listdir(VISANN_PATH)))
|
||||
for file in os.listdir(VISANN_PATH):
|
||||
image_path = VISIMG_PATH + '/' + file.replace('txt', 'jpg')
|
||||
ann_file = VISANN_PATH + '/' + file
|
||||
out_file = open(YOLO_LABELS_PATH + '/' + file, 'w')
|
||||
bbox = pd.read_csv(ann_file,header=None).values
|
||||
img = Image.open(image_path)
|
||||
img_size = img.size
|
||||
for row in bbox:
|
||||
if(row[4]==1 and 0<row[5]<11):
|
||||
label = convert(row[:4], img_size)
|
||||
out_file.write(str(row[5]-1) + " " + " ".join(str(f'{x:.6f}') for x in label) + '\n')
|
||||
out_file.close()
|
||||
|
||||
if __name__ == '__main__':
|
||||
ChangeToYolo5()
|
||||
|
|
@ -0,0 +1,67 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/
|
||||
# Example usage: python train.py --data Argoverse.yaml
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── Argoverse ← downloads here
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: ../datasets/Argoverse # dataset root dir
|
||||
train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images
|
||||
val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images
|
||||
test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
|
||||
|
||||
# Classes
|
||||
nc: 8 # number of classes
|
||||
names: ['person', 'bicycle', 'car', 'motorcycle', 'bus', 'truck', 'traffic_light', 'stop_sign'] # class names
|
||||
|
||||
|
||||
# Download script/URL (optional) ---------------------------------------------------------------------------------------
|
||||
download: |
|
||||
import json
|
||||
|
||||
from tqdm import tqdm
|
||||
from utils.general import download, Path
|
||||
|
||||
|
||||
def argoverse2yolo(set):
|
||||
labels = {}
|
||||
a = json.load(open(set, "rb"))
|
||||
for annot in tqdm(a['annotations'], desc=f"Converting {set} to YOLOv5 format..."):
|
||||
img_id = annot['image_id']
|
||||
img_name = a['images'][img_id]['name']
|
||||
img_label_name = img_name[:-3] + "txt"
|
||||
|
||||
cls = annot['category_id'] # instance class id
|
||||
x_center, y_center, width, height = annot['bbox']
|
||||
x_center = (x_center + width / 2) / 1920.0 # offset and scale
|
||||
y_center = (y_center + height / 2) / 1200.0 # offset and scale
|
||||
width /= 1920.0 # scale
|
||||
height /= 1200.0 # scale
|
||||
|
||||
img_dir = set.parents[2] / 'Argoverse-1.1' / 'labels' / a['seq_dirs'][a['images'][annot['image_id']]['sid']]
|
||||
if not img_dir.exists():
|
||||
img_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
k = str(img_dir / img_label_name)
|
||||
if k not in labels:
|
||||
labels[k] = []
|
||||
labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n")
|
||||
|
||||
for k in labels:
|
||||
with open(k, "w") as f:
|
||||
f.writelines(labels[k])
|
||||
|
||||
|
||||
# Download
|
||||
dir = Path('../datasets/Argoverse') # dataset root dir
|
||||
urls = ['https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip']
|
||||
download(urls, dir=dir, delete=False)
|
||||
|
||||
# Convert
|
||||
annotations_dir = 'Argoverse-HD/annotations/'
|
||||
(dir / 'Argoverse-1.1' / 'tracking').rename(dir / 'Argoverse-1.1' / 'images') # rename 'tracking' to 'images'
|
||||
for d in "train.json", "val.json":
|
||||
argoverse2yolo(dir / annotations_dir / d) # convert VisDrone annotations to YOLO labels
|
||||
|
|
@ -0,0 +1,53 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Global Wheat 2020 dataset http://www.global-wheat.com/
|
||||
# Example usage: python train.py --data GlobalWheat2020.yaml
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── GlobalWheat2020 ← downloads here
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: ../datasets/GlobalWheat2020 # dataset root dir
|
||||
train: # train images (relative to 'path') 3422 images
|
||||
- images/arvalis_1
|
||||
- images/arvalis_2
|
||||
- images/arvalis_3
|
||||
- images/ethz_1
|
||||
- images/rres_1
|
||||
- images/inrae_1
|
||||
- images/usask_1
|
||||
val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1)
|
||||
- images/ethz_1
|
||||
test: # test images (optional) 1276 images
|
||||
- images/utokyo_1
|
||||
- images/utokyo_2
|
||||
- images/nau_1
|
||||
- images/uq_1
|
||||
|
||||
# Classes
|
||||
nc: 1 # number of classes
|
||||
names: ['wheat_head'] # class names
|
||||
|
||||
|
||||
# Download script/URL (optional) ---------------------------------------------------------------------------------------
|
||||
download: |
|
||||
from utils.general import download, Path
|
||||
|
||||
# Download
|
||||
dir = Path(yaml['path']) # dataset root dir
|
||||
urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
|
||||
'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
|
||||
download(urls, dir=dir)
|
||||
|
||||
# Make Directories
|
||||
for p in 'annotations', 'images', 'labels':
|
||||
(dir / p).mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Move
|
||||
for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
|
||||
'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
|
||||
(dir / p).rename(dir / 'images' / p) # move to /images
|
||||
f = (dir / p).with_suffix('.json') # json file
|
||||
if f.exists():
|
||||
f.rename((dir / 'annotations' / p).with_suffix('.json')) # move to /annotations
|
||||
|
|
@ -0,0 +1,112 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Objects365 dataset https://www.objects365.org/
|
||||
# Example usage: python train.py --data Objects365.yaml
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── Objects365 ← downloads here
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: ../datasets/Objects365 # dataset root dir
|
||||
train: images/train # train images (relative to 'path') 1742289 images
|
||||
val: images/val # val images (relative to 'path') 80000 images
|
||||
test: # test images (optional)
|
||||
|
||||
# Classes
|
||||
nc: 365 # number of classes
|
||||
names: ['Person', 'Sneakers', 'Chair', 'Other Shoes', 'Hat', 'Car', 'Lamp', 'Glasses', 'Bottle', 'Desk', 'Cup',
|
||||
'Street Lights', 'Cabinet/shelf', 'Handbag/Satchel', 'Bracelet', 'Plate', 'Picture/Frame', 'Helmet', 'Book',
|
||||
'Gloves', 'Storage box', 'Boat', 'Leather Shoes', 'Flower', 'Bench', 'Potted Plant', 'Bowl/Basin', 'Flag',
|
||||
'Pillow', 'Boots', 'Vase', 'Microphone', 'Necklace', 'Ring', 'SUV', 'Wine Glass', 'Belt', 'Monitor/TV',
|
||||
'Backpack', 'Umbrella', 'Traffic Light', 'Speaker', 'Watch', 'Tie', 'Trash bin Can', 'Slippers', 'Bicycle',
|
||||
'Stool', 'Barrel/bucket', 'Van', 'Couch', 'Sandals', 'Basket', 'Drum', 'Pen/Pencil', 'Bus', 'Wild Bird',
|
||||
'High Heels', 'Motorcycle', 'Guitar', 'Carpet', 'Cell Phone', 'Bread', 'Camera', 'Canned', 'Truck',
|
||||
'Traffic cone', 'Cymbal', 'Lifesaver', 'Towel', 'Stuffed Toy', 'Candle', 'Sailboat', 'Laptop', 'Awning',
|
||||
'Bed', 'Faucet', 'Tent', 'Horse', 'Mirror', 'Power outlet', 'Sink', 'Apple', 'Air Conditioner', 'Knife',
|
||||
'Hockey Stick', 'Paddle', 'Pickup Truck', 'Fork', 'Traffic Sign', 'Balloon', 'Tripod', 'Dog', 'Spoon', 'Clock',
|
||||
'Pot', 'Cow', 'Cake', 'Dinning Table', 'Sheep', 'Hanger', 'Blackboard/Whiteboard', 'Napkin', 'Other Fish',
|
||||
'Orange/Tangerine', 'Toiletry', 'Keyboard', 'Tomato', 'Lantern', 'Machinery Vehicle', 'Fan',
|
||||
'Green Vegetables', 'Banana', 'Baseball Glove', 'Airplane', 'Mouse', 'Train', 'Pumpkin', 'Soccer', 'Skiboard',
|
||||
'Luggage', 'Nightstand', 'Tea pot', 'Telephone', 'Trolley', 'Head Phone', 'Sports Car', 'Stop Sign',
|
||||
'Dessert', 'Scooter', 'Stroller', 'Crane', 'Remote', 'Refrigerator', 'Oven', 'Lemon', 'Duck', 'Baseball Bat',
|
||||
'Surveillance Camera', 'Cat', 'Jug', 'Broccoli', 'Piano', 'Pizza', 'Elephant', 'Skateboard', 'Surfboard',
|
||||
'Gun', 'Skating and Skiing shoes', 'Gas stove', 'Donut', 'Bow Tie', 'Carrot', 'Toilet', 'Kite', 'Strawberry',
|
||||
'Other Balls', 'Shovel', 'Pepper', 'Computer Box', 'Toilet Paper', 'Cleaning Products', 'Chopsticks',
|
||||
'Microwave', 'Pigeon', 'Baseball', 'Cutting/chopping Board', 'Coffee Table', 'Side Table', 'Scissors',
|
||||
'Marker', 'Pie', 'Ladder', 'Snowboard', 'Cookies', 'Radiator', 'Fire Hydrant', 'Basketball', 'Zebra', 'Grape',
|
||||
'Giraffe', 'Potato', 'Sausage', 'Tricycle', 'Violin', 'Egg', 'Fire Extinguisher', 'Candy', 'Fire Truck',
|
||||
'Billiards', 'Converter', 'Bathtub', 'Wheelchair', 'Golf Club', 'Briefcase', 'Cucumber', 'Cigar/Cigarette',
|
||||
'Paint Brush', 'Pear', 'Heavy Truck', 'Hamburger', 'Extractor', 'Extension Cord', 'Tong', 'Tennis Racket',
|
||||
'Folder', 'American Football', 'earphone', 'Mask', 'Kettle', 'Tennis', 'Ship', 'Swing', 'Coffee Machine',
|
||||
'Slide', 'Carriage', 'Onion', 'Green beans', 'Projector', 'Frisbee', 'Washing Machine/Drying Machine',
|
||||
'Chicken', 'Printer', 'Watermelon', 'Saxophone', 'Tissue', 'Toothbrush', 'Ice cream', 'Hot-air balloon',
|
||||
'Cello', 'French Fries', 'Scale', 'Trophy', 'Cabbage', 'Hot dog', 'Blender', 'Peach', 'Rice', 'Wallet/Purse',
|
||||
'Volleyball', 'Deer', 'Goose', 'Tape', 'Tablet', 'Cosmetics', 'Trumpet', 'Pineapple', 'Golf Ball',
|
||||
'Ambulance', 'Parking meter', 'Mango', 'Key', 'Hurdle', 'Fishing Rod', 'Medal', 'Flute', 'Brush', 'Penguin',
|
||||
'Megaphone', 'Corn', 'Lettuce', 'Garlic', 'Swan', 'Helicopter', 'Green Onion', 'Sandwich', 'Nuts',
|
||||
'Speed Limit Sign', 'Induction Cooker', 'Broom', 'Trombone', 'Plum', 'Rickshaw', 'Goldfish', 'Kiwi fruit',
|
||||
'Router/modem', 'Poker Card', 'Toaster', 'Shrimp', 'Sushi', 'Cheese', 'Notepaper', 'Cherry', 'Pliers', 'CD',
|
||||
'Pasta', 'Hammer', 'Cue', 'Avocado', 'Hamimelon', 'Flask', 'Mushroom', 'Screwdriver', 'Soap', 'Recorder',
|
||||
'Bear', 'Eggplant', 'Board Eraser', 'Coconut', 'Tape Measure/Ruler', 'Pig', 'Showerhead', 'Globe', 'Chips',
|
||||
'Steak', 'Crosswalk Sign', 'Stapler', 'Camel', 'Formula 1', 'Pomegranate', 'Dishwasher', 'Crab',
|
||||
'Hoverboard', 'Meat ball', 'Rice Cooker', 'Tuba', 'Calculator', 'Papaya', 'Antelope', 'Parrot', 'Seal',
|
||||
'Butterfly', 'Dumbbell', 'Donkey', 'Lion', 'Urinal', 'Dolphin', 'Electric Drill', 'Hair Dryer', 'Egg tart',
|
||||
'Jellyfish', 'Treadmill', 'Lighter', 'Grapefruit', 'Game board', 'Mop', 'Radish', 'Baozi', 'Target', 'French',
|
||||
'Spring Rolls', 'Monkey', 'Rabbit', 'Pencil Case', 'Yak', 'Red Cabbage', 'Binoculars', 'Asparagus', 'Barbell',
|
||||
'Scallop', 'Noddles', 'Comb', 'Dumpling', 'Oyster', 'Table Tennis paddle', 'Cosmetics Brush/Eyeliner Pencil',
|
||||
'Chainsaw', 'Eraser', 'Lobster', 'Durian', 'Okra', 'Lipstick', 'Cosmetics Mirror', 'Curling', 'Table Tennis']
|
||||
|
||||
|
||||
# Download script/URL (optional) ---------------------------------------------------------------------------------------
|
||||
download: |
|
||||
from pycocotools.coco import COCO
|
||||
from tqdm import tqdm
|
||||
|
||||
from utils.general import Path, download, np, xyxy2xywhn
|
||||
|
||||
# Make Directories
|
||||
dir = Path(yaml['path']) # dataset root dir
|
||||
for p in 'images', 'labels':
|
||||
(dir / p).mkdir(parents=True, exist_ok=True)
|
||||
for q in 'train', 'val':
|
||||
(dir / p / q).mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Train, Val Splits
|
||||
for split, patches in [('train', 50 + 1), ('val', 43 + 1)]:
|
||||
print(f"Processing {split} in {patches} patches ...")
|
||||
images, labels = dir / 'images' / split, dir / 'labels' / split
|
||||
|
||||
# Download
|
||||
url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/"
|
||||
if split == 'train':
|
||||
download([f'{url}zhiyuan_objv2_{split}.tar.gz'], dir=dir, delete=False) # annotations json
|
||||
download([f'{url}patch{i}.tar.gz' for i in range(patches)], dir=images, curl=True, delete=False, threads=8)
|
||||
elif split == 'val':
|
||||
download([f'{url}zhiyuan_objv2_{split}.json'], dir=dir, delete=False) # annotations json
|
||||
download([f'{url}images/v1/patch{i}.tar.gz' for i in range(15 + 1)], dir=images, curl=True, delete=False, threads=8)
|
||||
download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, delete=False, threads=8)
|
||||
|
||||
# Move
|
||||
for f in tqdm(images.rglob('*.jpg'), desc=f'Moving {split} images'):
|
||||
f.rename(images / f.name) # move to /images/{split}
|
||||
|
||||
# Labels
|
||||
coco = COCO(dir / f'zhiyuan_objv2_{split}.json')
|
||||
names = [x["name"] for x in coco.loadCats(coco.getCatIds())]
|
||||
for cid, cat in enumerate(names):
|
||||
catIds = coco.getCatIds(catNms=[cat])
|
||||
imgIds = coco.getImgIds(catIds=catIds)
|
||||
for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'):
|
||||
width, height = im["width"], im["height"]
|
||||
path = Path(im["file_name"]) # image filename
|
||||
try:
|
||||
with open(labels / path.with_suffix('.txt').name, 'a') as file:
|
||||
annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None)
|
||||
for a in coco.loadAnns(annIds):
|
||||
x, y, w, h = a['bbox'] # bounding box in xywh (xy top-left corner)
|
||||
xyxy = np.array([x, y, x + w, y + h])[None] # pixels(1,4)
|
||||
x, y, w, h = xyxy2xywhn(xyxy, w=width, h=height, clip=True)[0] # normalized and clipped
|
||||
file.write(f"{cid} {x:.5f} {y:.5f} {w:.5f} {h:.5f}\n")
|
||||
except Exception as e:
|
||||
print(e)
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19
|
||||
# Example usage: python train.py --data SKU-110K.yaml
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── SKU-110K ← downloads here
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: ../datasets/SKU-110K # dataset root dir
|
||||
train: train.txt # train images (relative to 'path') 8219 images
|
||||
val: val.txt # val images (relative to 'path') 588 images
|
||||
test: test.txt # test images (optional) 2936 images
|
||||
|
||||
# Classes
|
||||
nc: 1 # number of classes
|
||||
names: ['object'] # class names
|
||||
|
||||
|
||||
# Download script/URL (optional) ---------------------------------------------------------------------------------------
|
||||
download: |
|
||||
import shutil
|
||||
from tqdm import tqdm
|
||||
from utils.general import np, pd, Path, download, xyxy2xywh
|
||||
|
||||
# Download
|
||||
dir = Path(yaml['path']) # dataset root dir
|
||||
parent = Path(dir.parent) # download dir
|
||||
urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz']
|
||||
download(urls, dir=parent, delete=False)
|
||||
|
||||
# Rename directories
|
||||
if dir.exists():
|
||||
shutil.rmtree(dir)
|
||||
(parent / 'SKU110K_fixed').rename(dir) # rename dir
|
||||
(dir / 'labels').mkdir(parents=True, exist_ok=True) # create labels dir
|
||||
|
||||
# Convert labels
|
||||
names = 'image', 'x1', 'y1', 'x2', 'y2', 'class', 'image_width', 'image_height' # column names
|
||||
for d in 'annotations_train.csv', 'annotations_val.csv', 'annotations_test.csv':
|
||||
x = pd.read_csv(dir / 'annotations' / d, names=names).values # annotations
|
||||
images, unique_images = x[:, 0], np.unique(x[:, 0])
|
||||
with open((dir / d).with_suffix('.txt').__str__().replace('annotations_', ''), 'w') as f:
|
||||
f.writelines(f'./images/{s}\n' for s in unique_images)
|
||||
for im in tqdm(unique_images, desc=f'Converting {dir / d}'):
|
||||
cls = 0 # single-class dataset
|
||||
with open((dir / 'labels' / im).with_suffix('.txt'), 'a') as f:
|
||||
for r in x[images == im]:
|
||||
w, h = r[6], r[7] # image width, height
|
||||
xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0] # instance
|
||||
f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n") # write label
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# UAVDT dataset
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: # dataset root dir
|
||||
train: # train images (relative to 'path')
|
||||
val: # val images (relative to 'path')
|
||||
test:
|
||||
|
||||
# Classes
|
||||
nc: 3 # number of classes
|
||||
names: ['car', 'truck', 'bus']
|
||||
|
|
@ -0,0 +1,80 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC
|
||||
# Example usage: python train.py --data VOC.yaml
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── VOC ← downloads here
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: ../datasets/VOC
|
||||
train: # train images (relative to 'path') 16551 images
|
||||
- images/train2012
|
||||
- images/train2007
|
||||
- images/val2012
|
||||
- images/val2007
|
||||
val: # val images (relative to 'path') 4952 images
|
||||
- images/test2007
|
||||
test: # test images (optional)
|
||||
- images/test2007
|
||||
|
||||
# Classes
|
||||
nc: 20 # number of classes
|
||||
names: ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
|
||||
'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor'] # class names
|
||||
|
||||
|
||||
# Download script/URL (optional) ---------------------------------------------------------------------------------------
|
||||
download: |
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
from tqdm import tqdm
|
||||
from utils.general import download, Path
|
||||
|
||||
|
||||
def convert_label(path, lb_path, year, image_id):
|
||||
def convert_box(size, box):
|
||||
dw, dh = 1. / size[0], 1. / size[1]
|
||||
x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
|
||||
return x * dw, y * dh, w * dw, h * dh
|
||||
|
||||
in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml')
|
||||
out_file = open(lb_path, 'w')
|
||||
tree = ET.parse(in_file)
|
||||
root = tree.getroot()
|
||||
size = root.find('size')
|
||||
w = int(size.find('width').text)
|
||||
h = int(size.find('height').text)
|
||||
|
||||
for obj in root.iter('object'):
|
||||
cls = obj.find('name').text
|
||||
if cls in yaml['names'] and not int(obj.find('difficult').text) == 1:
|
||||
xmlbox = obj.find('bndbox')
|
||||
bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')])
|
||||
cls_id = yaml['names'].index(cls) # class id
|
||||
out_file.write(" ".join([str(a) for a in (cls_id, *bb)]) + '\n')
|
||||
|
||||
|
||||
# Download
|
||||
dir = Path(yaml['path']) # dataset root dir
|
||||
url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
|
||||
urls = [url + 'VOCtrainval_06-Nov-2007.zip', # 446MB, 5012 images
|
||||
url + 'VOCtest_06-Nov-2007.zip', # 438MB, 4953 images
|
||||
url + 'VOCtrainval_11-May-2012.zip'] # 1.95GB, 17126 images
|
||||
download(urls, dir=dir / 'images', delete=False)
|
||||
|
||||
# Convert
|
||||
path = dir / f'images/VOCdevkit'
|
||||
for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'):
|
||||
imgs_path = dir / 'images' / f'{image_set}{year}'
|
||||
lbs_path = dir / 'labels' / f'{image_set}{year}'
|
||||
imgs_path.mkdir(exist_ok=True, parents=True)
|
||||
lbs_path.mkdir(exist_ok=True, parents=True)
|
||||
|
||||
image_ids = open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt').read().strip().split()
|
||||
for id in tqdm(image_ids, desc=f'{image_set}{year}'):
|
||||
f = path / f'VOC{year}/JPEGImages/{id}.jpg' # old img path
|
||||
lb_path = (lbs_path / f.name).with_suffix('.txt') # new label path
|
||||
f.rename(imgs_path / f.name) # move image
|
||||
convert_label(path, lb_path, year, id) # convert labels to YOLO format
|
||||
|
|
@ -0,0 +1,61 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset
|
||||
# Example usage: python train.py --data VisDrone.yaml
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── VisDrone ← downloads here
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: ../datasets/VisDrone # dataset root dir
|
||||
train: VisDrone2019-DET-train/images # train images (relative to 'path') 6471 images
|
||||
val: VisDrone2019-DET-val/images # val images (relative to 'path') 548 images
|
||||
test: VisDrone2019-DET-test-challenge/images # test images (optional) 1610 images
|
||||
|
||||
# Classes
|
||||
nc: 10 # number of classes
|
||||
names: ['pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor']
|
||||
|
||||
|
||||
# Download script/URL (optional) ---------------------------------------------------------------------------------------
|
||||
download: |
|
||||
from utils.general import download, os, Path
|
||||
|
||||
def visdrone2yolo(dir):
|
||||
from PIL import Image
|
||||
from tqdm import tqdm
|
||||
|
||||
def convert_box(size, box):
|
||||
# Convert VisDrone box to YOLO xywh box
|
||||
dw = 1. / size[0]
|
||||
dh = 1. / size[1]
|
||||
return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh
|
||||
|
||||
(dir / 'labels').mkdir(parents=True, exist_ok=True) # make labels directory
|
||||
pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}')
|
||||
for f in pbar:
|
||||
img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size
|
||||
lines = []
|
||||
with open(f, 'r') as file: # read annotation.txt
|
||||
for row in [x.split(',') for x in file.read().strip().splitlines()]:
|
||||
if row[4] == '0': # VisDrone 'ignored regions' class 0
|
||||
continue
|
||||
cls = int(row[5]) - 1
|
||||
box = convert_box(img_size, tuple(map(int, row[:4])))
|
||||
lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n")
|
||||
with open(str(f).replace(os.sep + 'annotations' + os.sep, os.sep + 'labels' + os.sep), 'w') as fl:
|
||||
fl.writelines(lines) # write label.txt
|
||||
|
||||
|
||||
# Download
|
||||
dir = Path(yaml['path']) # dataset root dir
|
||||
urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip',
|
||||
'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip',
|
||||
'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip',
|
||||
'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip']
|
||||
download(urls, dir=dir)
|
||||
|
||||
# Convert
|
||||
for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev':
|
||||
visdrone2yolo(dir / d) # convert VisDrone annotations to YOLO labels
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# COCO 2017 dataset http://cocodataset.org
|
||||
# Example usage: python train.py --data coco.yaml
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── coco ← downloads here
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: ../datasets/coco # dataset root dir
|
||||
train: train2017.txt # train images (relative to 'path') 118287 images
|
||||
val: val2017.txt # train images (relative to 'path') 5000 images
|
||||
test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
|
||||
|
||||
# Classes
|
||||
nc: 80 # number of classes
|
||||
names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
|
||||
'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
|
||||
'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
|
||||
'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
|
||||
'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
|
||||
'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
|
||||
'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
|
||||
'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
|
||||
'hair drier', 'toothbrush'] # class names
|
||||
|
||||
|
||||
# Download script/URL (optional)
|
||||
download: |
|
||||
from utils.general import download, Path
|
||||
|
||||
# Download labels
|
||||
segments = False # segment or box labels
|
||||
dir = Path(yaml['path']) # dataset root dir
|
||||
url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
|
||||
urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')] # labels
|
||||
download(urls, dir=dir.parent)
|
||||
|
||||
# Download data
|
||||
urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images
|
||||
'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images
|
||||
'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional)
|
||||
download(urls, dir=dir / 'images', threads=3)
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017)
|
||||
# Example usage: python train.py --data coco128.yaml
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── coco128 ← downloads here
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: ../datasets/coco128 # dataset root dir
|
||||
train: images/train2017 # train images (relative to 'path') 128 images
|
||||
val: images/train2017 # val images (relative to 'path') 128 images
|
||||
test: # test images (optional)
|
||||
|
||||
# Classes
|
||||
nc: 80 # number of classes
|
||||
names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
|
||||
'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
|
||||
'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
|
||||
'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
|
||||
'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
|
||||
'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
|
||||
'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
|
||||
'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
|
||||
'hair drier', 'toothbrush'] # class names
|
||||
|
||||
|
||||
# Download script/URL (optional)
|
||||
download: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
lr0: 0.0032
|
||||
lrf: 0.12
|
||||
momentum: 0.843
|
||||
weight_decay: 0.00036
|
||||
warmup_epochs: 2.0
|
||||
warmup_momentum: 0.5
|
||||
warmup_bias_lr: 0.05
|
||||
box: 0.07
|
||||
cls: 0.18
|
||||
cls_pw: 0.631
|
||||
obj: 0.15
|
||||
obj_pw: 0.911
|
||||
iou_t: 0.2
|
||||
anchor_t: 3
|
||||
fl_gamma: 0.0
|
||||
hsv_h: 0.4
|
||||
hsv_s: 0.3
|
||||
hsv_v: 0.5
|
||||
degrees: 0.2
|
||||
translate: 0.0
|
||||
scale: 0.4
|
||||
shear: 0.0
|
||||
perspective: 0.0
|
||||
flipud: 0.0
|
||||
fliplr: 0.5
|
||||
mosaic: 1.0
|
||||
mixup: 0.2
|
||||
copy_paste: 0.0
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
lr0: 0.0032
|
||||
lrf: 0.12
|
||||
momentum: 0.843
|
||||
weight_decay: 0.00036
|
||||
warmup_epochs: 2.0
|
||||
warmup_momentum: 0.5
|
||||
warmup_bias_lr: 0.05
|
||||
box: 0.07
|
||||
cls: 0.18
|
||||
cls_pw: 0.631
|
||||
obj: 0.15
|
||||
obj_pw: 0.911
|
||||
iou_t: 0.2
|
||||
anchor_t: 3
|
||||
fl_gamma: 0.0
|
||||
hsv_h: 0.4
|
||||
hsv_s: 0.3
|
||||
hsv_v: 0.5
|
||||
degrees: 0.2
|
||||
translate: 0.0
|
||||
scale: 0.4
|
||||
shear: 0.0
|
||||
perspective: 0.0
|
||||
flipud: 0.0
|
||||
fliplr: 0.5
|
||||
mosaic: 1.0
|
||||
mixup: 0.2
|
||||
copy_paste: 0.0
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Hyperparameters for VOC finetuning
|
||||
# python train.py --batch 64 --weights yolov5m.pt --data VOC.yaml --img 512 --epochs 50
|
||||
# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
|
||||
|
||||
# Hyperparameter Evolution Results
|
||||
# Generations: 306
|
||||
# P R mAP.5 mAP.5:.95 box obj cls
|
||||
# Metrics: 0.6 0.936 0.896 0.684 0.0115 0.00805 0.00146
|
||||
|
||||
lr0: 0.0032
|
||||
lrf: 0.12
|
||||
momentum: 0.843
|
||||
weight_decay: 0.00036
|
||||
warmup_epochs: 2.0
|
||||
warmup_momentum: 0.5
|
||||
warmup_bias_lr: 0.05
|
||||
box: 0.0296
|
||||
cls: 0.243
|
||||
cls_pw: 0.631
|
||||
obj: 0.301
|
||||
obj_pw: 0.911
|
||||
iou_t: 0.2
|
||||
anchor_t: 2.91
|
||||
# anchors: 3.63
|
||||
fl_gamma: 0.0
|
||||
hsv_h: 0.0138
|
||||
hsv_s: 0.664
|
||||
hsv_v: 0.464
|
||||
degrees: 0.373
|
||||
translate: 0.245
|
||||
scale: 0.898
|
||||
shear: 0.602
|
||||
perspective: 0.0
|
||||
flipud: 0.00856
|
||||
fliplr: 0.5
|
||||
mosaic: 1.0
|
||||
mixup: 0.243
|
||||
copy_paste: 0.0
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
lr0: 0.00258
|
||||
lrf: 0.17
|
||||
momentum: 0.779
|
||||
weight_decay: 0.00058
|
||||
warmup_epochs: 1.33
|
||||
warmup_momentum: 0.86
|
||||
warmup_bias_lr: 0.0711
|
||||
box: 0.0539
|
||||
cls: 0.299
|
||||
cls_pw: 0.825
|
||||
obj: 0.632
|
||||
obj_pw: 1.0
|
||||
iou_t: 0.2
|
||||
anchor_t: 3.44
|
||||
anchors: 3.2
|
||||
fl_gamma: 0.0
|
||||
hsv_h: 0.0188
|
||||
hsv_s: 0.704
|
||||
hsv_v: 0.36
|
||||
degrees: 0.0
|
||||
translate: 0.0902
|
||||
scale: 0.491
|
||||
shear: 0.0
|
||||
perspective: 0.0
|
||||
flipud: 0.0
|
||||
fliplr: 0.5
|
||||
mosaic: 1.0
|
||||
mixup: 0.0
|
||||
copy_paste: 0.0
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Hyperparameters for high-augmentation COCO training from scratch
|
||||
# python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300
|
||||
# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
|
||||
|
||||
lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
|
||||
lrf: 0.2 # final OneCycleLR learning rate (lr0 * lrf)
|
||||
momentum: 0.937 # SGD momentum/Adam beta1
|
||||
weight_decay: 0.0005 # optimizer weight decay 5e-4
|
||||
warmup_epochs: 3.0 # warmup epochs (fractions ok)
|
||||
warmup_momentum: 0.8 # warmup initial momentum
|
||||
warmup_bias_lr: 0.1 # warmup initial bias lr
|
||||
box: 0.05 # box loss gain
|
||||
cls: 0.3 # cls loss gain
|
||||
cls_pw: 1.0 # cls BCELoss positive_weight
|
||||
obj: 0.7 # obj loss gain (scale with pixels)
|
||||
obj_pw: 1.0 # obj BCELoss positive_weight
|
||||
iou_t: 0.20 # IoU training threshold
|
||||
anchor_t: 4.0 # anchor-multiple threshold
|
||||
# anchors: 3 # anchors per output layer (0 to ignore)
|
||||
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
|
||||
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
|
||||
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
|
||||
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
|
||||
degrees: 0.0 # image rotation (+/- deg)
|
||||
translate: 0.1 # image translation (+/- fraction)
|
||||
scale: 0.9 # image scale (+/- gain)
|
||||
shear: 0.0 # image shear (+/- deg)
|
||||
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
|
||||
flipud: 0.0 # image flip up-down (probability)
|
||||
fliplr: 0.5 # image flip left-right (probability)
|
||||
mosaic: 1.0 # image mosaic (probability)
|
||||
mixup: 0.1 # image mixup (probability)
|
||||
copy_paste: 0.1 # segment copy-paste (probability)
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Hyperparameters for low-augmentation COCO training from scratch
|
||||
# python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear
|
||||
# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
|
||||
|
||||
lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
|
||||
lrf: 0.01 # final OneCycleLR learning rate (lr0 * lrf)
|
||||
momentum: 0.937 # SGD momentum/Adam beta1
|
||||
weight_decay: 0.0005 # optimizer weight decay 5e-4
|
||||
warmup_epochs: 3.0 # warmup epochs (fractions ok)
|
||||
warmup_momentum: 0.8 # warmup initial momentum
|
||||
warmup_bias_lr: 0.1 # warmup initial bias lr
|
||||
box: 0.05 # box loss gain
|
||||
cls: 0.5 # cls loss gain
|
||||
cls_pw: 1.0 # cls BCELoss positive_weight
|
||||
obj: 1.0 # obj loss gain (scale with pixels)
|
||||
obj_pw: 1.0 # obj BCELoss positive_weight
|
||||
iou_t: 0.20 # IoU training threshold
|
||||
anchor_t: 4.0 # anchor-multiple threshold
|
||||
# anchors: 3 # anchors per output layer (0 to ignore)
|
||||
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
|
||||
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
|
||||
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
|
||||
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
|
||||
degrees: 0.0 # image rotation (+/- deg)
|
||||
translate: 0.1 # image translation (+/- fraction)
|
||||
scale: 0.5 # image scale (+/- gain)
|
||||
shear: 0.0 # image shear (+/- deg)
|
||||
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
|
||||
flipud: 0.0 # image flip up-down (probability)
|
||||
fliplr: 0.5 # image flip left-right (probability)
|
||||
mosaic: 1.0 # image mosaic (probability)
|
||||
mixup: 0.0 # image mixup (probability)
|
||||
copy_paste: 0.0 # segment copy-paste (probability)
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Hyperparameters for medium-augmentation COCO training from scratch
|
||||
# python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300
|
||||
# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
|
||||
|
||||
lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
|
||||
lrf: 0.1 # final OneCycleLR learning rate (lr0 * lrf)
|
||||
momentum: 0.937 # SGD momentum/Adam beta1
|
||||
weight_decay: 0.0005 # optimizer weight decay 5e-4
|
||||
warmup_epochs: 3.0 # warmup epochs (fractions ok)
|
||||
warmup_momentum: 0.8 # warmup initial momentum
|
||||
warmup_bias_lr: 0.1 # warmup initial bias lr
|
||||
box: 0.05 # box loss gain
|
||||
cls: 0.3 # cls loss gain
|
||||
cls_pw: 1.0 # cls BCELoss positive_weight
|
||||
obj: 0.7 # obj loss gain (scale with pixels)
|
||||
obj_pw: 1.0 # obj BCELoss positive_weight
|
||||
iou_t: 0.20 # IoU training threshold
|
||||
anchor_t: 4.0 # anchor-multiple threshold
|
||||
# anchors: 3 # anchors per output layer (0 to ignore)
|
||||
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
|
||||
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
|
||||
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
|
||||
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
|
||||
degrees: 0.0 # image rotation (+/- deg)
|
||||
translate: 0.1 # image translation (+/- fraction)
|
||||
scale: 0.9 # image scale (+/- gain)
|
||||
shear: 0.0 # image shear (+/- deg)
|
||||
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
|
||||
flipud: 0.0 # image flip up-down (probability)
|
||||
fliplr: 0.5 # image flip left-right (probability)
|
||||
mosaic: 1.0 # image mosaic (probability)
|
||||
mixup: 0.1 # image mixup (probability)
|
||||
copy_paste: 0.0 # segment copy-paste (probability)
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Hyperparameters for COCO training from scratch
|
||||
# python train.py --batch 40 --cfg yolov5m.yaml --weights '' --data coco.yaml --img 640 --epochs 300
|
||||
# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
|
||||
|
||||
lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
|
||||
lrf: 0.1 # final OneCycleLR learning rate (lr0 * lrf)
|
||||
momentum: 0.937 # SGD momentum/Adam beta1
|
||||
weight_decay: 0.0005 # optimizer weight decay 5e-4
|
||||
warmup_epochs: 3.0 # warmup epochs (fractions ok)
|
||||
warmup_momentum: 0.8 # warmup initial momentum
|
||||
warmup_bias_lr: 0.1 # warmup initial bias lr
|
||||
box: 0.05 # box loss gain
|
||||
cls: 0.5 # cls loss gain
|
||||
cls_pw: 1.0 # cls BCELoss positive_weight
|
||||
obj: 1.0 # obj loss gain (scale with pixels)
|
||||
obj_pw: 1.0 # obj BCELoss positive_weight
|
||||
iou_t: 0.20 # IoU training threshold
|
||||
anchor_t: 4.0 # anchor-multiple threshold
|
||||
# anchors: 3 # anchors per output layer (0 to ignore)
|
||||
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
|
||||
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
|
||||
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
|
||||
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
|
||||
degrees: 0.0 # image rotation (+/- deg)
|
||||
translate: 0.1 # image translation (+/- fraction)
|
||||
scale: 0.5 # image scale (+/- gain)
|
||||
shear: 0.0 # image shear (+/- deg)
|
||||
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
|
||||
flipud: 0.0 # image flip up-down (probability)
|
||||
fliplr: 0.5 # image flip left-right (probability)
|
||||
mosaic: 1.0 # image mosaic (probability)
|
||||
mixup: 0.0 # image mixup (probability)
|
||||
copy_paste: 0.0 # segment copy-paste (probability)
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 476 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 165 KiB |
|
|
@ -0,0 +1,20 @@
|
|||
#!/bin/bash
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Download latest models from https://github.com/ultralytics/yolov5/releases
|
||||
# Example usage: bash path/to/download_weights.sh
|
||||
# parent
|
||||
# └── yolov5
|
||||
# ├── yolov5s.pt ← downloads here
|
||||
# ├── yolov5m.pt
|
||||
# └── ...
|
||||
|
||||
python - <<EOF
|
||||
from utils.downloads import attempt_download
|
||||
|
||||
models = ['n', 's', 'm', 'l', 'x']
|
||||
models.extend([x + '6' for x in models]) # add P6 models
|
||||
|
||||
for x in models:
|
||||
attempt_download(f'yolov5{x}.pt')
|
||||
|
||||
EOF
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
#!/bin/bash
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Download COCO 2017 dataset http://cocodataset.org
|
||||
# Example usage: bash data/scripts/get_coco.sh
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── coco ← downloads here
|
||||
|
||||
# Download/unzip labels
|
||||
d='../datasets' # unzip directory
|
||||
url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
|
||||
f='coco2017labels.zip' # or 'coco2017labels-segments.zip', 68 MB
|
||||
echo 'Downloading' $url$f ' ...'
|
||||
curl -L $url$f -o $f && unzip -q $f -d $d && rm $f &
|
||||
|
||||
# Download/unzip images
|
||||
d='../datasets/coco/images' # unzip directory
|
||||
url=http://images.cocodataset.org/zips/
|
||||
f1='train2017.zip' # 19G, 118k images
|
||||
f2='val2017.zip' # 1G, 5k images
|
||||
f3='test2017.zip' # 7G, 41k images (optional)
|
||||
for f in $f1 $f2; do
|
||||
echo 'Downloading' $url$f '...'
|
||||
curl -L $url$f -o $f && unzip -q $f -d $d && rm $f &
|
||||
done
|
||||
wait # finish background tasks
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
#!/bin/bash
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Download COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017)
|
||||
# Example usage: bash data/scripts/get_coco128.sh
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── coco128 ← downloads here
|
||||
|
||||
# Download/unzip images and labels
|
||||
d='../datasets' # unzip directory
|
||||
url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
|
||||
f='coco128.zip' # or 'coco128-segments.zip', 68 MB
|
||||
echo 'Downloading' $url$f ' ...'
|
||||
curl -L $url$f -o $f && unzip -q $f -d $d && rm $f &
|
||||
|
||||
wait # finish background tasks
|
||||
|
|
@ -0,0 +1,102 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# xView 2018 dataset https://challenge.xviewdataset.org
|
||||
# -------- DOWNLOAD DATA MANUALLY from URL above and unzip to 'datasets/xView' before running train command! --------
|
||||
# Example usage: python train.py --data xView.yaml
|
||||
# parent
|
||||
# ├── yolov5
|
||||
# └── datasets
|
||||
# └── xView ← downloads here
|
||||
|
||||
|
||||
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
|
||||
path: ../datasets/xView # dataset root dir
|
||||
train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images
|
||||
val: images/autosplit_val.txt # train images (relative to 'path') 10% of 847 train images
|
||||
|
||||
# Classes
|
||||
nc: 60 # number of classes
|
||||
names: ['Fixed-wing Aircraft', 'Small Aircraft', 'Cargo Plane', 'Helicopter', 'Passenger Vehicle', 'Small Car', 'Bus',
|
||||
'Pickup Truck', 'Utility Truck', 'Truck', 'Cargo Truck', 'Truck w/Box', 'Truck Tractor', 'Trailer',
|
||||
'Truck w/Flatbed', 'Truck w/Liquid', 'Crane Truck', 'Railway Vehicle', 'Passenger Car', 'Cargo Car',
|
||||
'Flat Car', 'Tank car', 'Locomotive', 'Maritime Vessel', 'Motorboat', 'Sailboat', 'Tugboat', 'Barge',
|
||||
'Fishing Vessel', 'Ferry', 'Yacht', 'Container Ship', 'Oil Tanker', 'Engineering Vehicle', 'Tower crane',
|
||||
'Container Crane', 'Reach Stacker', 'Straddle Carrier', 'Mobile Crane', 'Dump Truck', 'Haul Truck',
|
||||
'Scraper/Tractor', 'Front loader/Bulldozer', 'Excavator', 'Cement Mixer', 'Ground Grader', 'Hut/Tent', 'Shed',
|
||||
'Building', 'Aircraft Hangar', 'Damaged Building', 'Facility', 'Construction Site', 'Vehicle Lot', 'Helipad',
|
||||
'Storage Tank', 'Shipping container lot', 'Shipping Container', 'Pylon', 'Tower'] # class names
|
||||
|
||||
|
||||
# Download script/URL (optional) ---------------------------------------------------------------------------------------
|
||||
download: |
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
from tqdm import tqdm
|
||||
|
||||
from utils.datasets import autosplit
|
||||
from utils.general import download, xyxy2xywhn
|
||||
|
||||
|
||||
def convert_labels(fname=Path('xView/xView_train.geojson')):
|
||||
# Convert xView geoJSON labels to YOLO format
|
||||
path = fname.parent
|
||||
with open(fname) as f:
|
||||
print(f'Loading {fname}...')
|
||||
data = json.load(f)
|
||||
|
||||
# Make dirs
|
||||
labels = Path(path / 'labels' / 'train')
|
||||
os.system(f'rm -rf {labels}')
|
||||
labels.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# xView classes 11-94 to 0-59
|
||||
xview_class2index = [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, -1, 9, 10, 11,
|
||||
12, 13, 14, 15, -1, -1, 16, 17, 18, 19, 20, 21, 22, -1, 23, 24, 25, -1, 26, 27, -1, 28, -1,
|
||||
29, 30, 31, 32, 33, 34, 35, 36, 37, -1, 38, 39, 40, 41, 42, 43, 44, 45, -1, -1, -1, -1, 46,
|
||||
47, 48, 49, -1, 50, 51, -1, 52, -1, -1, -1, 53, 54, -1, 55, -1, -1, 56, -1, 57, -1, 58, 59]
|
||||
|
||||
shapes = {}
|
||||
for feature in tqdm(data['features'], desc=f'Converting {fname}'):
|
||||
p = feature['properties']
|
||||
if p['bounds_imcoords']:
|
||||
id = p['image_id']
|
||||
file = path / 'train_images' / id
|
||||
if file.exists(): # 1395.tif missing
|
||||
try:
|
||||
box = np.array([int(num) for num in p['bounds_imcoords'].split(",")])
|
||||
assert box.shape[0] == 4, f'incorrect box shape {box.shape[0]}'
|
||||
cls = p['type_id']
|
||||
cls = xview_class2index[int(cls)] # xView class to 0-60
|
||||
assert 59 >= cls >= 0, f'incorrect class index {cls}'
|
||||
|
||||
# Write YOLO label
|
||||
if id not in shapes:
|
||||
shapes[id] = Image.open(file).size
|
||||
box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True)
|
||||
with open((labels / id).with_suffix('.txt'), 'a') as f:
|
||||
f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n") # write label.txt
|
||||
except Exception as e:
|
||||
print(f'WARNING: skipping one label for {file}: {e}')
|
||||
|
||||
|
||||
# Download manually from https://challenge.xviewdataset.org
|
||||
dir = Path(yaml['path']) # dataset root dir
|
||||
# urls = ['https://d307kc0mrhucc3.cloudfront.net/train_labels.zip', # train labels
|
||||
# 'https://d307kc0mrhucc3.cloudfront.net/train_images.zip', # 15G, 847 train images
|
||||
# 'https://d307kc0mrhucc3.cloudfront.net/val_images.zip'] # 5G, 282 val images (no labels)
|
||||
# download(urls, dir=dir, delete=False)
|
||||
|
||||
# Convert labels
|
||||
convert_labels(dir / 'xView_train.geojson')
|
||||
|
||||
# Move images
|
||||
images = Path(dir / 'images')
|
||||
images.mkdir(parents=True, exist_ok=True)
|
||||
Path(dir / 'train_images').rename(dir / 'images' / 'train')
|
||||
Path(dir / 'val_images').rename(dir / 'images' / 'val')
|
||||
|
||||
# Split
|
||||
autosplit(dir / 'images' / 'train')
|
||||
|
|
@ -0,0 +1,317 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Run inference on images, videos, directories, streams, etc.
|
||||
|
||||
Usage:
|
||||
$ python path/to/detect.py --source path/to/img.jpg --weights yolov5s.pt --img 640
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import platform
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.backends.cudnn as cudnn
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[0] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
|
||||
|
||||
from models.experimental import attempt_load
|
||||
from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
|
||||
from utils.general import (LOGGER, apply_classifier, check_file, check_img_size, check_imshow, check_requirements,
|
||||
check_suffix, colorstr, increment_path, non_max_suppression, print_args, save_one_box,
|
||||
scale_coords, strip_optimizer, xyxy2xywh)
|
||||
from utils.plots import Annotator, colors
|
||||
from utils.torch_utils import load_classifier, select_device, time_sync
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s)
|
||||
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
|
||||
imgsz=640, # inference size (pixels)
|
||||
conf_thres=0.25, # confidence threshold
|
||||
iou_thres=0.45, # NMS IOU threshold
|
||||
max_det=1000, # maximum detections per image
|
||||
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
||||
view_img=False, # show results
|
||||
save_txt=False, # save results to *.txt
|
||||
save_conf=False, # save confidences in --save-txt labels
|
||||
save_crop=False, # save cropped prediction boxes
|
||||
nosave=False, # do not save images/videos
|
||||
classes=None, # filter by class: --class 0, or --class 0 2 3
|
||||
agnostic_nms=False, # class-agnostic NMS
|
||||
augment=False, # augmented inference
|
||||
visualize=False, # visualize features
|
||||
update=False, # update all models
|
||||
project=ROOT / 'runs/detect', # save results to project/name
|
||||
name='exp', # save results to project/name
|
||||
exist_ok=False, # existing project/name ok, do not increment
|
||||
line_thickness=3, # bounding box thickness (pixels)
|
||||
hide_labels=False, # hide labels
|
||||
hide_conf=False, # hide confidences
|
||||
half=False, # use FP16 half-precision inference
|
||||
dnn=False, # use OpenCV DNN for ONNX inference
|
||||
):
|
||||
source = str(source)
|
||||
save_img = not nosave and not source.endswith('.txt') # save inference images
|
||||
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
|
||||
is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
|
||||
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
|
||||
if is_url and is_file:
|
||||
source = check_file(source) # download
|
||||
|
||||
# Directories
|
||||
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
|
||||
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
|
||||
|
||||
# Initialize
|
||||
device = select_device(device)
|
||||
half &= device.type != 'cpu' # half precision only supported on CUDA
|
||||
|
||||
# Load model
|
||||
w = str(weights[0] if isinstance(weights, list) else weights)
|
||||
classify, suffix, suffixes = False, Path(w).suffix.lower(), ['.pt', '.onnx', '.tflite', '.pb', '']
|
||||
check_suffix(w, suffixes) # check weights have acceptable suffix
|
||||
pt, onnx, tflite, pb, saved_model = (suffix == x for x in suffixes) # backend booleans
|
||||
stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults
|
||||
if pt:
|
||||
model = torch.jit.load(w) if 'torchscript' in w else attempt_load(weights, map_location=device)
|
||||
stride = int(model.stride.max()) # model stride
|
||||
names = model.module.names if hasattr(model, 'module') else model.names # get class names
|
||||
if half:
|
||||
model.half() # to FP16
|
||||
if classify: # second-stage classifier
|
||||
modelc = load_classifier(name='resnet50', n=2) # initialize
|
||||
modelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval()
|
||||
elif onnx:
|
||||
if dnn:
|
||||
check_requirements(('opencv-python>=4.5.4',))
|
||||
net = cv2.dnn.readNetFromONNX(w)
|
||||
else:
|
||||
check_requirements(('onnx', 'onnxruntime-gpu' if torch.has_cuda else 'onnxruntime'))
|
||||
import onnxruntime
|
||||
session = onnxruntime.InferenceSession(w, None)
|
||||
else: # TensorFlow models
|
||||
import tensorflow as tf
|
||||
if pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
|
||||
def wrap_frozen_graph(gd, inputs, outputs):
|
||||
x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped import
|
||||
return x.prune(tf.nest.map_structure(x.graph.as_graph_element, inputs),
|
||||
tf.nest.map_structure(x.graph.as_graph_element, outputs))
|
||||
|
||||
graph_def = tf.Graph().as_graph_def()
|
||||
graph_def.ParseFromString(open(w, 'rb').read())
|
||||
frozen_func = wrap_frozen_graph(gd=graph_def, inputs="x:0", outputs="Identity:0")
|
||||
elif saved_model:
|
||||
model = tf.keras.models.load_model(w)
|
||||
elif tflite:
|
||||
if "edgetpu" in w: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
|
||||
import tflite_runtime.interpreter as tflri
|
||||
delegate = {'Linux': 'libedgetpu.so.1', # install libedgetpu https://coral.ai/software/#edgetpu-runtime
|
||||
'Darwin': 'libedgetpu.1.dylib',
|
||||
'Windows': 'edgetpu.dll'}[platform.system()]
|
||||
interpreter = tflri.Interpreter(model_path=w, experimental_delegates=[tflri.load_delegate(delegate)])
|
||||
else:
|
||||
interpreter = tf.lite.Interpreter(model_path=w) # load TFLite model
|
||||
interpreter.allocate_tensors() # allocate
|
||||
input_details = interpreter.get_input_details() # inputs
|
||||
output_details = interpreter.get_output_details() # outputs
|
||||
int8 = input_details[0]['dtype'] == np.uint8 # is TFLite quantized uint8 model
|
||||
imgsz = check_img_size(imgsz, s=stride) # check image size
|
||||
|
||||
# Dataloader
|
||||
if webcam:
|
||||
view_img = check_imshow()
|
||||
cudnn.benchmark = True # set True to speed up constant image size inference
|
||||
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
|
||||
bs = len(dataset) # batch_size
|
||||
else:
|
||||
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
|
||||
bs = 1 # batch_size
|
||||
vid_path, vid_writer = [None] * bs, [None] * bs
|
||||
|
||||
# Run inference
|
||||
if pt and device.type != 'cpu':
|
||||
model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.parameters()))) # run once
|
||||
dt, seen = [0.0, 0.0, 0.0], 0
|
||||
for path, img, im0s, vid_cap, s in dataset:
|
||||
t1 = time_sync()
|
||||
if onnx:
|
||||
img = img.astype('float32')
|
||||
else:
|
||||
img = torch.from_numpy(img).to(device)
|
||||
img = img.half() if half else img.float() # uint8 to fp16/32
|
||||
img /= 255 # 0 - 255 to 0.0 - 1.0
|
||||
if len(img.shape) == 3:
|
||||
img = img[None] # expand for batch dim
|
||||
t2 = time_sync()
|
||||
dt[0] += t2 - t1
|
||||
|
||||
# Inference
|
||||
if pt:
|
||||
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
|
||||
pred = model(img, augment=augment, visualize=visualize)[0]
|
||||
elif onnx:
|
||||
if dnn:
|
||||
net.setInput(img)
|
||||
pred = torch.tensor(net.forward())
|
||||
else:
|
||||
pred = torch.tensor(session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img}))
|
||||
else: # tensorflow model (tflite, pb, saved_model)
|
||||
imn = img.permute(0, 2, 3, 1).cpu().numpy() # image in numpy
|
||||
if pb:
|
||||
pred = frozen_func(x=tf.constant(imn)).numpy()
|
||||
elif saved_model:
|
||||
pred = model(imn, training=False).numpy()
|
||||
elif tflite:
|
||||
if int8:
|
||||
scale, zero_point = input_details[0]['quantization']
|
||||
imn = (imn / scale + zero_point).astype(np.uint8) # de-scale
|
||||
interpreter.set_tensor(input_details[0]['index'], imn)
|
||||
interpreter.invoke()
|
||||
pred = interpreter.get_tensor(output_details[0]['index'])
|
||||
if int8:
|
||||
scale, zero_point = output_details[0]['quantization']
|
||||
pred = (pred.astype(np.float32) - zero_point) * scale # re-scale
|
||||
pred[..., 0] *= imgsz[1] # x
|
||||
pred[..., 1] *= imgsz[0] # y
|
||||
pred[..., 2] *= imgsz[1] # w
|
||||
pred[..., 3] *= imgsz[0] # h
|
||||
pred = torch.tensor(pred)
|
||||
t3 = time_sync()
|
||||
dt[1] += t3 - t2
|
||||
|
||||
# NMS
|
||||
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
|
||||
dt[2] += time_sync() - t3
|
||||
|
||||
# Second-stage classifier (optional)
|
||||
if classify:
|
||||
pred = apply_classifier(pred, modelc, img, im0s)
|
||||
|
||||
# Process predictions
|
||||
for i, det in enumerate(pred): # per image
|
||||
seen += 1
|
||||
if webcam: # batch_size >= 1
|
||||
p, im0, frame = path[i], im0s[i].copy(), dataset.count
|
||||
s += f'{i}: '
|
||||
else:
|
||||
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
|
||||
|
||||
p = Path(p) # to Path
|
||||
save_path = str(save_dir / p.name) # img.jpg
|
||||
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
|
||||
s += '%gx%g ' % img.shape[2:] # print string
|
||||
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
|
||||
imc = im0.copy() if save_crop else im0 # for save_crop
|
||||
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
|
||||
if len(det):
|
||||
# Rescale boxes from img_size to im0 size
|
||||
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
|
||||
|
||||
# Print results
|
||||
for c in det[:, -1].unique():
|
||||
n = (det[:, -1] == c).sum() # detections per class
|
||||
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
|
||||
|
||||
# Write results
|
||||
for *xyxy, conf, cls in reversed(det):
|
||||
if save_txt: # Write to file
|
||||
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
|
||||
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
|
||||
with open(txt_path + '.txt', 'a') as f:
|
||||
f.write(('%g ' * len(line)).rstrip() % line + '\n')
|
||||
|
||||
if save_img or save_crop or view_img: # Add bbox to image
|
||||
c = int(cls) # integer class
|
||||
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
|
||||
annotator.box_label(xyxy, label, color=colors(c, True))
|
||||
if save_crop:
|
||||
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
|
||||
|
||||
# Print time (inference-only)
|
||||
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
|
||||
|
||||
# Stream results
|
||||
im0 = annotator.result()
|
||||
if view_img:
|
||||
cv2.imshow(str(p), im0)
|
||||
cv2.waitKey(1) # 1 millisecond
|
||||
|
||||
# Save results (image with detections)
|
||||
if save_img:
|
||||
if dataset.mode == 'image':
|
||||
cv2.imwrite(save_path, im0)
|
||||
else: # 'video' or 'stream'
|
||||
if vid_path[i] != save_path: # new video
|
||||
vid_path[i] = save_path
|
||||
if isinstance(vid_writer[i], cv2.VideoWriter):
|
||||
vid_writer[i].release() # release previous video writer
|
||||
if vid_cap: # video
|
||||
fps = vid_cap.get(cv2.CAP_PROP_FPS)
|
||||
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||||
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||||
else: # stream
|
||||
fps, w, h = 30, im0.shape[1], im0.shape[0]
|
||||
save_path += '.mp4'
|
||||
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
|
||||
vid_writer[i].write(im0)
|
||||
|
||||
# Print results
|
||||
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
|
||||
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
|
||||
if save_txt or save_img:
|
||||
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
|
||||
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
|
||||
if update:
|
||||
strip_optimizer(weights) # update model (to fix SourceChangeWarning)
|
||||
|
||||
|
||||
def parse_opt():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'weights/yolov5l-xs-1.pt', help='model path(s)')
|
||||
parser.add_argument('--source', type=str, default=ROOT / 'image_test', help='file/dir/URL/glob, 0 for webcam')
|
||||
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
|
||||
parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
|
||||
parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
|
||||
parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--view-img', action='store_true', help='show results')
|
||||
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
|
||||
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
|
||||
parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
|
||||
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
|
||||
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
|
||||
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
|
||||
parser.add_argument('--augment', action='store_true', help='augmented inference')
|
||||
parser.add_argument('--visualize', action='store_true', help='visualize features')
|
||||
parser.add_argument('--update', action='store_true', help='update all models')
|
||||
parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
|
||||
parser.add_argument('--name', default='exp', help='save results to project/name')
|
||||
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
|
||||
parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
|
||||
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
|
||||
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
|
||||
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
|
||||
parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
|
||||
opt = parser.parse_args()
|
||||
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
|
||||
print_args(FILE.stem, opt)
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
check_requirements(exclude=('tensorboard', 'thop'))
|
||||
run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
|
|
@ -0,0 +1,366 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Export a YOLOv5 PyTorch model to TorchScript, ONNX, CoreML, TensorFlow (saved_model, pb, TFLite, TF.js,) formats
|
||||
TensorFlow exports authored by https://github.com/zldrobit
|
||||
|
||||
Usage:
|
||||
$ python path/to/export.py --weights yolov5s.pt --include torchscript onnx coreml saved_model pb tflite tfjs
|
||||
|
||||
Inference:
|
||||
$ python path/to/detect.py --weights yolov5s.pt
|
||||
yolov5s.onnx (must export with --dynamic)
|
||||
yolov5s_saved_model
|
||||
yolov5s.pb
|
||||
yolov5s.tflite
|
||||
|
||||
TensorFlow.js:
|
||||
$ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example
|
||||
$ npm install
|
||||
$ ln -s ../../yolov5/yolov5s_web_model public/yolov5s_web_model
|
||||
$ npm start
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torch.utils.mobile_optimizer import optimize_for_mobile
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[0] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
|
||||
|
||||
from models.common import Conv
|
||||
from models.experimental import attempt_load
|
||||
from models.yolo import Detect
|
||||
from utils.activations import SiLU
|
||||
from utils.datasets import LoadImages
|
||||
from utils.general import (LOGGER, check_dataset, check_img_size, check_requirements, colorstr, file_size, print_args,
|
||||
url2file)
|
||||
from utils.torch_utils import select_device
|
||||
|
||||
|
||||
def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')):
|
||||
# YOLOv5 TorchScript model export
|
||||
try:
|
||||
LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...')
|
||||
f = file.with_suffix('.torchscript.pt')
|
||||
|
||||
ts = torch.jit.trace(model, im, strict=False)
|
||||
(optimize_for_mobile(ts) if optimize else ts).save(f)
|
||||
|
||||
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
except Exception as e:
|
||||
LOGGER.info(f'{prefix} export failure: {e}')
|
||||
|
||||
|
||||
def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:')):
|
||||
# YOLOv5 ONNX export
|
||||
try:
|
||||
check_requirements(('onnx',))
|
||||
import onnx
|
||||
|
||||
LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...')
|
||||
f = file.with_suffix('.onnx')
|
||||
|
||||
torch.onnx.export(model, im, f, verbose=False, opset_version=opset,
|
||||
training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
|
||||
do_constant_folding=not train,
|
||||
input_names=['images'],
|
||||
output_names=['output'],
|
||||
dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # shape(1,3,640,640)
|
||||
'output': {0: 'batch', 1: 'anchors'} # shape(1,25200,85)
|
||||
} if dynamic else None)
|
||||
|
||||
# Checks
|
||||
model_onnx = onnx.load(f) # load onnx model
|
||||
onnx.checker.check_model(model_onnx) # check onnx model
|
||||
# LOGGER.info(onnx.helper.printable_graph(model_onnx.graph)) # print
|
||||
|
||||
# Simplify
|
||||
if simplify:
|
||||
try:
|
||||
check_requirements(('onnx-simplifier',))
|
||||
import onnxsim
|
||||
|
||||
LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
|
||||
model_onnx, check = onnxsim.simplify(
|
||||
model_onnx,
|
||||
dynamic_input_shape=dynamic,
|
||||
input_shapes={'images': list(im.shape)} if dynamic else None)
|
||||
assert check, 'assert check failed'
|
||||
onnx.save(model_onnx, f)
|
||||
except Exception as e:
|
||||
LOGGER.info(f'{prefix} simplifier failure: {e}')
|
||||
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
LOGGER.info(f"{prefix} run --dynamic ONNX model inference with: 'python detect.py --weights {f}'")
|
||||
except Exception as e:
|
||||
LOGGER.info(f'{prefix} export failure: {e}')
|
||||
|
||||
|
||||
def export_coreml(model, im, file, prefix=colorstr('CoreML:')):
|
||||
# YOLOv5 CoreML export
|
||||
ct_model = None
|
||||
try:
|
||||
check_requirements(('coremltools',))
|
||||
import coremltools as ct
|
||||
|
||||
LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...')
|
||||
f = file.with_suffix('.mlmodel')
|
||||
|
||||
model.train() # CoreML exports should be placed in model.train() mode
|
||||
ts = torch.jit.trace(model, im, strict=False) # TorchScript model
|
||||
ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])])
|
||||
ct_model.save(f)
|
||||
|
||||
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
except Exception as e:
|
||||
LOGGER.info(f'\n{prefix} export failure: {e}')
|
||||
|
||||
return ct_model
|
||||
|
||||
|
||||
def export_saved_model(model, im, file, dynamic,
|
||||
tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
|
||||
conf_thres=0.25, prefix=colorstr('TensorFlow saved_model:')):
|
||||
# YOLOv5 TensorFlow saved_model export
|
||||
keras_model = None
|
||||
try:
|
||||
import tensorflow as tf
|
||||
from tensorflow import keras
|
||||
|
||||
from models.tf import TFDetect, TFModel
|
||||
|
||||
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
|
||||
f = str(file).replace('.pt', '_saved_model')
|
||||
batch_size, ch, *imgsz = list(im.shape) # BCHW
|
||||
|
||||
tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
|
||||
im = tf.zeros((batch_size, *imgsz, 3)) # BHWC order for TensorFlow
|
||||
y = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
|
||||
inputs = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
|
||||
outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
|
||||
keras_model = keras.Model(inputs=inputs, outputs=outputs)
|
||||
keras_model.trainable = False
|
||||
keras_model.summary()
|
||||
keras_model.save(f, save_format='tf')
|
||||
|
||||
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
except Exception as e:
|
||||
LOGGER.info(f'\n{prefix} export failure: {e}')
|
||||
|
||||
return keras_model
|
||||
|
||||
|
||||
def export_pb(keras_model, im, file, prefix=colorstr('TensorFlow GraphDef:')):
|
||||
# YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
|
||||
try:
|
||||
import tensorflow as tf
|
||||
from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
|
||||
|
||||
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
|
||||
f = file.with_suffix('.pb')
|
||||
|
||||
m = tf.function(lambda x: keras_model(x)) # full model
|
||||
m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype))
|
||||
frozen_func = convert_variables_to_constants_v2(m)
|
||||
frozen_func.graph.as_graph_def()
|
||||
tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False)
|
||||
|
||||
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
except Exception as e:
|
||||
LOGGER.info(f'\n{prefix} export failure: {e}')
|
||||
|
||||
|
||||
def export_tflite(keras_model, im, file, int8, data, ncalib, prefix=colorstr('TensorFlow Lite:')):
|
||||
# YOLOv5 TensorFlow Lite export
|
||||
try:
|
||||
import tensorflow as tf
|
||||
|
||||
from models.tf import representative_dataset_gen
|
||||
|
||||
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
|
||||
batch_size, ch, *imgsz = list(im.shape) # BCHW
|
||||
f = str(file).replace('.pt', '-fp16.tflite')
|
||||
|
||||
converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
|
||||
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
|
||||
converter.target_spec.supported_types = [tf.float16]
|
||||
converter.optimizations = [tf.lite.Optimize.DEFAULT]
|
||||
if int8:
|
||||
dataset = LoadImages(check_dataset(data)['train'], img_size=imgsz, auto=False) # representative data
|
||||
converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib)
|
||||
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
|
||||
converter.target_spec.supported_types = []
|
||||
converter.inference_input_type = tf.uint8 # or tf.int8
|
||||
converter.inference_output_type = tf.uint8 # or tf.int8
|
||||
converter.experimental_new_quantizer = False
|
||||
f = str(file).replace('.pt', '-int8.tflite')
|
||||
|
||||
tflite_model = converter.convert()
|
||||
open(f, "wb").write(tflite_model)
|
||||
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
|
||||
except Exception as e:
|
||||
LOGGER.info(f'\n{prefix} export failure: {e}')
|
||||
|
||||
|
||||
def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')):
|
||||
# YOLOv5 TensorFlow.js export
|
||||
try:
|
||||
check_requirements(('tensorflowjs',))
|
||||
import re
|
||||
|
||||
import tensorflowjs as tfjs
|
||||
|
||||
LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...')
|
||||
f = str(file).replace('.pt', '_web_model') # js dir
|
||||
f_pb = file.with_suffix('.pb') # *.pb path
|
||||
f_json = f + '/model.json' # *.json path
|
||||
|
||||
cmd = f"tensorflowjs_converter --input_format=tf_frozen_model " \
|
||||
f"--output_node_names='Identity,Identity_1,Identity_2,Identity_3' {f_pb} {f}"
|
||||
subprocess.run(cmd, shell=True)
|
||||
|
||||
json = open(f_json).read()
|
||||
with open(f_json, 'w') as j: # sort JSON Identity_* in ascending order
|
||||
subst = re.sub(
|
||||
r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
|
||||
r'"Identity.?.?": {"name": "Identity.?.?"}, '
|
||||
r'"Identity.?.?": {"name": "Identity.?.?"}, '
|
||||
r'"Identity.?.?": {"name": "Identity.?.?"}}}',
|
||||
r'{"outputs": {"Identity": {"name": "Identity"}, '
|
||||
r'"Identity_1": {"name": "Identity_1"}, '
|
||||
r'"Identity_2": {"name": "Identity_2"}, '
|
||||
r'"Identity_3": {"name": "Identity_3"}}}',
|
||||
json)
|
||||
j.write(subst)
|
||||
|
||||
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
except Exception as e:
|
||||
LOGGER.info(f'\n{prefix} export failure: {e}')
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def run(data=ROOT / 'data/coco128.yaml', # 'dataset.yaml path'
|
||||
weights=ROOT / 'yolov5s.pt', # weights path
|
||||
imgsz=(640, 640), # image (height, width)
|
||||
batch_size=1, # batch size
|
||||
device='cpu', # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
||||
include=('torchscript', 'onnx', 'coreml'), # include formats
|
||||
half=False, # FP16 half-precision export
|
||||
inplace=False, # set YOLOv5 Detect() inplace=True
|
||||
train=False, # model.train() mode
|
||||
optimize=False, # TorchScript: optimize for mobile
|
||||
int8=False, # CoreML/TF INT8 quantization
|
||||
dynamic=False, # ONNX/TF: dynamic axes
|
||||
simplify=False, # ONNX: simplify model
|
||||
opset=12, # ONNX: opset version
|
||||
topk_per_class=100, # TF.js NMS: topk per class to keep
|
||||
topk_all=100, # TF.js NMS: topk for all classes to keep
|
||||
iou_thres=0.45, # TF.js NMS: IoU threshold
|
||||
conf_thres=0.25 # TF.js NMS: confidence threshold
|
||||
):
|
||||
t = time.time()
|
||||
include = [x.lower() for x in include]
|
||||
tf_exports = list(x in include for x in ('saved_model', 'pb', 'tflite', 'tfjs')) # TensorFlow exports
|
||||
imgsz *= 2 if len(imgsz) == 1 else 1 # expand
|
||||
file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else weights)
|
||||
|
||||
# Load PyTorch model
|
||||
device = select_device(device)
|
||||
assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0'
|
||||
model = attempt_load(weights, map_location=device, inplace=True, fuse=True) # load FP32 model
|
||||
nc, names = model.nc, model.names # number of classes, class names
|
||||
|
||||
# Input
|
||||
gs = int(max(model.stride)) # grid size (max stride)
|
||||
imgsz = [check_img_size(x, gs) for x in imgsz] # verify img_size are gs-multiples
|
||||
im = torch.zeros(batch_size, 3, *imgsz).to(device) # image size(1,3,320,192) BCHW iDetection
|
||||
|
||||
# Update model
|
||||
if half:
|
||||
im, model = im.half(), model.half() # to FP16
|
||||
model.train() if train else model.eval() # training mode = no Detect() layer grid construction
|
||||
for k, m in model.named_modules():
|
||||
if isinstance(m, Conv): # assign export-friendly activations
|
||||
if isinstance(m.act, nn.SiLU):
|
||||
m.act = SiLU()
|
||||
elif isinstance(m, Detect):
|
||||
m.inplace = inplace
|
||||
m.onnx_dynamic = dynamic
|
||||
# m.forward = m.forward_export # assign forward (optional)
|
||||
|
||||
for _ in range(2):
|
||||
y = model(im) # dry runs
|
||||
LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} ({file_size(file):.1f} MB)")
|
||||
|
||||
# Exports
|
||||
if 'torchscript' in include:
|
||||
export_torchscript(model, im, file, optimize)
|
||||
if 'onnx' in include:
|
||||
export_onnx(model, im, file, opset, train, dynamic, simplify)
|
||||
if 'coreml' in include:
|
||||
export_coreml(model, im, file)
|
||||
|
||||
# TensorFlow Exports
|
||||
if any(tf_exports):
|
||||
pb, tflite, tfjs = tf_exports[1:]
|
||||
assert not (tflite and tfjs), 'TFLite and TF.js models must be exported separately, please pass only one type.'
|
||||
model = export_saved_model(model, im, file, dynamic, tf_nms=tfjs, agnostic_nms=tfjs,
|
||||
topk_per_class=topk_per_class, topk_all=topk_all, conf_thres=conf_thres,
|
||||
iou_thres=iou_thres) # keras model
|
||||
if pb or tfjs: # pb prerequisite to tfjs
|
||||
export_pb(model, im, file)
|
||||
if tflite:
|
||||
export_tflite(model, im, file, int8=int8, data=data, ncalib=100)
|
||||
if tfjs:
|
||||
export_tfjs(model, im, file)
|
||||
|
||||
# Finish
|
||||
LOGGER.info(f'\nExport complete ({time.time() - t:.2f}s)'
|
||||
f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
|
||||
f'\nVisualize with https://netron.app')
|
||||
|
||||
|
||||
def parse_opt():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
|
||||
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
|
||||
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)')
|
||||
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
|
||||
parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
|
||||
parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True')
|
||||
parser.add_argument('--train', action='store_true', help='model.train() mode')
|
||||
parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile')
|
||||
parser.add_argument('--int8', action='store_true', help='CoreML/TF INT8 quantization')
|
||||
parser.add_argument('--dynamic', action='store_true', help='ONNX/TF: dynamic axes')
|
||||
parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model')
|
||||
parser.add_argument('--opset', type=int, default=13, help='ONNX: opset version')
|
||||
parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep')
|
||||
parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep')
|
||||
parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold')
|
||||
parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold')
|
||||
parser.add_argument('--include', nargs='+',
|
||||
default=['torchscript', 'onnx'],
|
||||
help='available formats are (torchscript, onnx, coreml, saved_model, pb, tflite, tfjs)')
|
||||
opt = parser.parse_args()
|
||||
print_args(FILE.stem, opt)
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
|
|
@ -0,0 +1,143 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5/
|
||||
|
||||
Usage:
|
||||
import torch
|
||||
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
|
||||
"""
|
||||
|
||||
import torch
|
||||
|
||||
|
||||
def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
"""Creates a specified YOLOv5 model
|
||||
|
||||
Arguments:
|
||||
name (str): name of model, i.e. 'yolov5s'
|
||||
pretrained (bool): load pretrained weights into the model
|
||||
channels (int): number of input channels
|
||||
classes (int): number of model classes
|
||||
autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
|
||||
verbose (bool): print all information to screen
|
||||
device (str, torch.device, None): device to use for model parameters
|
||||
|
||||
Returns:
|
||||
YOLOv5 pytorch model
|
||||
"""
|
||||
from pathlib import Path
|
||||
|
||||
from models.experimental import attempt_load
|
||||
from models.yolo import Model
|
||||
from utils.downloads import attempt_download
|
||||
from utils.general import check_requirements, set_logging
|
||||
from utils.torch_utils import select_device
|
||||
|
||||
file = Path(__file__).resolve()
|
||||
check_requirements(exclude=('tensorboard', 'thop', 'opencv-python'))
|
||||
set_logging(verbose=verbose)
|
||||
|
||||
save_dir = Path('') if str(name).endswith('.pt') else file.parent
|
||||
path = (save_dir / name).with_suffix('.pt') # checkpoint path
|
||||
try:
|
||||
device = select_device(('0' if torch.cuda.is_available() else 'cpu') if device is None else device)
|
||||
|
||||
if pretrained and channels == 3 and classes == 80:
|
||||
model = attempt_load(path, map_location=device) # download/load FP32 model
|
||||
else:
|
||||
cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0] # model.yaml path
|
||||
model = Model(cfg, channels, classes) # create model
|
||||
if pretrained:
|
||||
ckpt = torch.load(attempt_download(path), map_location=device) # load
|
||||
msd = model.state_dict() # model state_dict
|
||||
csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
|
||||
csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape} # filter
|
||||
model.load_state_dict(csd, strict=False) # load
|
||||
if len(ckpt['model'].names) == classes:
|
||||
model.names = ckpt['model'].names # set class names attribute
|
||||
if autoshape:
|
||||
model = model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS
|
||||
return model.to(device)
|
||||
|
||||
except Exception as e:
|
||||
help_url = 'https://github.com/ultralytics/yolov5/issues/36'
|
||||
s = 'Cache may be out of date, try `force_reload=True`. See %s for help.' % help_url
|
||||
raise Exception(s) from e
|
||||
|
||||
|
||||
def custom(path='path/to/model.pt', autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5 custom or local model
|
||||
return _create(path, autoshape=autoshape, verbose=verbose, device=device)
|
||||
|
||||
|
||||
def yolov5n(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-nano model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5n', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-small model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5s', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-medium model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5m', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-large model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5l', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-xlarge model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5x', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
def yolov5n6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-nano-P6 model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5n6', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-small-P6 model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5s6', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5m6', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-large-P6 model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5l6', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
|
||||
# YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5
|
||||
return _create('yolov5x6', pretrained, channels, classes, autoshape, verbose, device)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
model = _create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True) # pretrained
|
||||
# model = custom(path='path/to/model.pt') # custom
|
||||
|
||||
# Verify inference
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
|
||||
imgs = ['data/images/zidane.jpg', # filename
|
||||
Path('data/images/zidane.jpg'), # Path
|
||||
'https://ultralytics.com/images/zidane.jpg', # URI
|
||||
cv2.imread('data/images/bus.jpg')[:, :, ::-1], # OpenCV
|
||||
Image.open('data/images/bus.jpg'), # PIL
|
||||
np.zeros((320, 640, 3))] # numpy
|
||||
|
||||
results = model(imgs) # batched inference
|
||||
results.print()
|
||||
results.save()
|
||||
|
|
@ -0,0 +1 @@
|
|||
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,830 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Common modules
|
||||
"""
|
||||
|
||||
import logging
|
||||
import math
|
||||
import warnings
|
||||
from copy import copy
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import requests
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from PIL import Image
|
||||
from typing import Optional
|
||||
from torch.cuda import amp
|
||||
|
||||
from utils.datasets import exif_transpose, letterbox
|
||||
from utils.general import (colorstr, increment_path, make_divisible, non_max_suppression, save_one_box, scale_coords,
|
||||
xyxy2xywh)
|
||||
from utils.plots import Annotator, colors
|
||||
from utils.torch_utils import time_sync
|
||||
|
||||
LOGGER = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def autopad(k, p=None): # kernel, padding
|
||||
# Pad to 'same'
|
||||
if p is None:
|
||||
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
|
||||
return p
|
||||
|
||||
class Conv(nn.Module):
|
||||
# Standard convolution
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
|
||||
|
||||
def forward(self, x):
|
||||
return self.act(self.bn(self.conv(x)))
|
||||
|
||||
def forward_fuse(self, x):
|
||||
return self.act(self.conv(x))
|
||||
|
||||
|
||||
class DWConv(Conv):
|
||||
# Depth-wise convolution class
|
||||
def __init__(self, c1, c2, k=1, s=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
|
||||
|
||||
class ChannelAttentionModule(nn.Module):
|
||||
def __init__(self, c1, reduction=16):
|
||||
super(ChannelAttentionModule, self).__init__()
|
||||
mid_channel = c1 // reduction
|
||||
self.avg_pool = nn.AdaptiveAvgPool2d(1)
|
||||
self.max_pool = nn.AdaptiveMaxPool2d(1)
|
||||
self.shared_MLP = nn.Sequential(
|
||||
nn.Linear(in_features=c1, out_features=mid_channel),
|
||||
nn.ReLU(),
|
||||
nn.Linear(in_features=mid_channel, out_features=c1)
|
||||
)
|
||||
self.sigmoid = nn.Sigmoid()
|
||||
#self.act=SiLU()
|
||||
def forward(self, x):
|
||||
avgout = self.shared_MLP(self.avg_pool(x).view(x.size(0),-1)).unsqueeze(2).unsqueeze(3)
|
||||
maxout = self.shared_MLP(self.max_pool(x).view(x.size(0),-1)).unsqueeze(2).unsqueeze(3)
|
||||
return self.sigmoid(avgout + maxout)
|
||||
|
||||
class SpatialAttentionModule(nn.Module):
|
||||
def __init__(self):
|
||||
super(SpatialAttentionModule, self).__init__()
|
||||
self.conv2d = nn.Conv2d(in_channels=2, out_channels=1, kernel_size=7, stride=1, padding=3)
|
||||
#self.act=SiLU()
|
||||
self.sigmoid = nn.Sigmoid()
|
||||
def forward(self, x):
|
||||
avgout = torch.mean(x, dim=1, keepdim=True)
|
||||
maxout, _ = torch.max(x, dim=1, keepdim=True)
|
||||
out = torch.cat([avgout, maxout], dim=1)
|
||||
out = self.sigmoid(self.conv2d(out))
|
||||
return out
|
||||
|
||||
class CBAM(nn.Module):
|
||||
def __init__(self, c1,c2):
|
||||
super(CBAM, self).__init__()
|
||||
self.channel_attention = ChannelAttentionModule(c1)
|
||||
self.spatial_attention = SpatialAttentionModule()
|
||||
|
||||
def forward(self, x):
|
||||
out = self.channel_attention(x) * x
|
||||
out = self.spatial_attention(out) * out
|
||||
return out
|
||||
|
||||
class TransformerLayer(nn.Module):
|
||||
def __init__(self, c, num_heads):
|
||||
super().__init__()
|
||||
|
||||
self.ln1 = nn.LayerNorm(c)
|
||||
self.q = nn.Linear(c, c, bias=False)
|
||||
self.k = nn.Linear(c, c, bias=False)
|
||||
self.v = nn.Linear(c, c, bias=False)
|
||||
self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
|
||||
self.ln2 = nn.LayerNorm(c)
|
||||
self.fc1 = nn.Linear(c, 4*c, bias=False)
|
||||
self.fc2 = nn.Linear(4*c, c, bias=False)
|
||||
self.dropout = nn.Dropout(0.1)
|
||||
self.act = nn.ReLU(True)
|
||||
|
||||
def forward(self, x):
|
||||
x_ = self.ln1(x)
|
||||
x = self.dropout(self.ma(self.q(x_), self.k(x_), self.v(x_))[0]) + x
|
||||
x_ = self.ln2(x)
|
||||
x_ = self.fc2(self.dropout(self.act(self.fc1(x_))))
|
||||
x = x + self.dropout(x_)
|
||||
return x
|
||||
|
||||
|
||||
class TransformerBlock(nn.Module):
|
||||
# Vision Transformer https://arxiv.org/abs/2010.11929
|
||||
def __init__(self, c1, c2, num_heads, num_layers):
|
||||
super().__init__()
|
||||
self.conv = None
|
||||
if c1 != c2:
|
||||
self.conv = Conv(c1, c2)
|
||||
self.linear = nn.Linear(c2, c2) # learnable position embedding
|
||||
self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
|
||||
self.c2 = c2
|
||||
|
||||
def forward(self, x):
|
||||
if self.conv is not None:
|
||||
x = self.conv(x)
|
||||
b, _, w, h = x.shape
|
||||
p = x.flatten(2).unsqueeze(0).transpose(0, 3).squeeze(3)
|
||||
return self.tr(p + self.linear(p)).unsqueeze(3).transpose(0, 3).reshape(b, self.c2, w, h)
|
||||
|
||||
def drop_path_f(x, drop_prob: float = 0., training: bool = False):
|
||||
"""Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
|
||||
|
||||
This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
|
||||
the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
|
||||
See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
|
||||
changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
|
||||
'survival rate' as the argument.
|
||||
|
||||
"""
|
||||
if drop_prob == 0. or not training:
|
||||
return x
|
||||
keep_prob = 1 - drop_prob
|
||||
shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets
|
||||
random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
|
||||
random_tensor.floor_() # binarize
|
||||
output = x.div(keep_prob) * random_tensor
|
||||
return output
|
||||
|
||||
|
||||
class DropPath(nn.Module):
|
||||
"""Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
|
||||
"""
|
||||
def __init__(self, drop_prob=None):
|
||||
super(DropPath, self).__init__()
|
||||
self.drop_prob = drop_prob
|
||||
|
||||
def forward(self, x):
|
||||
return drop_path_f(x, self.drop_prob, self.training)
|
||||
|
||||
def window_partition(x, window_size: int):
|
||||
"""
|
||||
将feature map按照window_size划分成一个个没有重叠的window
|
||||
Args:
|
||||
x: (B, H, W, C)
|
||||
window_size (int): window size(M)
|
||||
|
||||
Returns:
|
||||
windows: (num_windows*B, window_size, window_size, C)
|
||||
"""
|
||||
B, H, W, C = x.shape
|
||||
x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
|
||||
# permute: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H//Mh, W//Mh, Mw, Mw, C]
|
||||
# view: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B*num_windows, Mh, Mw, C]
|
||||
windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
|
||||
return windows
|
||||
|
||||
def window_reverse(windows, window_size: int, H: int, W: int):
|
||||
"""
|
||||
将一个个window还原成一个feature map
|
||||
Args:
|
||||
windows: (num_windows*B, window_size, window_size, C)
|
||||
window_size (int): Window size(M)
|
||||
H (int): Height of image
|
||||
W (int): Width of image
|
||||
|
||||
Returns:
|
||||
x: (B, H, W, C)
|
||||
"""
|
||||
B = int(windows.shape[0] / (H * W / window_size / window_size))
|
||||
# view: [B*num_windows, Mh, Mw, C] -> [B, H//Mh, W//Mw, Mh, Mw, C]
|
||||
x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
|
||||
# permute: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B, H//Mh, Mh, W//Mw, Mw, C]
|
||||
# view: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H, W, C]
|
||||
x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
|
||||
return x
|
||||
|
||||
class Mlp(nn.Module):
|
||||
""" MLP as used in Vision Transformer, MLP-Mixer and related networks
|
||||
"""
|
||||
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
|
||||
super().__init__()
|
||||
out_features = out_features or in_features
|
||||
hidden_features = hidden_features or in_features
|
||||
|
||||
self.fc1 = nn.Linear(in_features, hidden_features)
|
||||
self.act = act_layer()
|
||||
self.drop1 = nn.Dropout(drop)
|
||||
self.fc2 = nn.Linear(hidden_features, out_features)
|
||||
self.drop2 = nn.Dropout(drop)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.fc1(x)
|
||||
x = self.act(x)
|
||||
x = self.drop1(x)
|
||||
x = self.fc2(x)
|
||||
x = self.drop2(x)
|
||||
return x
|
||||
|
||||
class WindowAttention(nn.Module):
|
||||
r""" Window based multi-head self attention (W-MSA) module with relative position bias.
|
||||
It supports both of shifted and non-shifted window.
|
||||
|
||||
Args:
|
||||
dim (int): Number of input channels.
|
||||
window_size (tuple[int]): The height and width of the window.
|
||||
num_heads (int): Number of attention heads.
|
||||
qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
|
||||
attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
|
||||
proj_drop (float, optional): Dropout ratio of output. Default: 0.0
|
||||
"""
|
||||
|
||||
def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0.):
|
||||
|
||||
super().__init__()
|
||||
self.dim = dim
|
||||
self.window_size = window_size # [Mh, Mw]
|
||||
self.num_heads = num_heads
|
||||
head_dim = dim // num_heads
|
||||
self.scale = head_dim ** -0.5
|
||||
|
||||
# define a parameter table of relative position bias
|
||||
self.relative_position_bias_table = nn.Parameter(
|
||||
torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads)) # [2*Mh-1 * 2*Mw-1, nH]
|
||||
|
||||
# get pair-wise relative position index for each token inside the window
|
||||
coords_h = torch.arange(self.window_size[0])
|
||||
coords_w = torch.arange(self.window_size[1])
|
||||
coords = torch.stack(torch.meshgrid([coords_h, coords_w], indexing="ij")) # [2, Mh, Mw]
|
||||
coords_flatten = torch.flatten(coords, 1) # [2, Mh*Mw]
|
||||
# [2, Mh*Mw, 1] - [2, 1, Mh*Mw]
|
||||
relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # [2, Mh*Mw, Mh*Mw]
|
||||
relative_coords = relative_coords.permute(1, 2, 0).contiguous() # [Mh*Mw, Mh*Mw, 2]
|
||||
relative_coords[:, :, 0] += self.window_size[0] - 1 # shift to start from 0
|
||||
relative_coords[:, :, 1] += self.window_size[1] - 1
|
||||
relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
|
||||
relative_position_index = relative_coords.sum(-1) # [Mh*Mw, Mh*Mw]
|
||||
self.register_buffer("relative_position_index", relative_position_index)
|
||||
|
||||
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
|
||||
self.attn_drop = nn.Dropout(attn_drop)
|
||||
self.proj = nn.Linear(dim, dim)
|
||||
self.proj_drop = nn.Dropout(proj_drop)
|
||||
|
||||
nn.init.trunc_normal_(self.relative_position_bias_table, std=.02)
|
||||
self.softmax = nn.Softmax(dim=-1)
|
||||
|
||||
def forward(self, x, mask: Optional[torch.Tensor] = None):
|
||||
"""
|
||||
Args:
|
||||
x: input features with shape of (num_windows*B, Mh*Mw, C)
|
||||
mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
|
||||
"""
|
||||
# [batch_size*num_windows, Mh*Mw, total_embed_dim]
|
||||
B_, N, C = x.shape
|
||||
# qkv(): -> [batch_size*num_windows, Mh*Mw, 3 * total_embed_dim]
|
||||
# reshape: -> [batch_size*num_windows, Mh*Mw, 3, num_heads, embed_dim_per_head]
|
||||
# permute: -> [3, batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
|
||||
qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
# [batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
|
||||
q, k, v = qkv.unbind(0) # make torchscript happy (cannot use tensor as tuple)
|
||||
|
||||
# transpose: -> [batch_size*num_windows, num_heads, embed_dim_per_head, Mh*Mw]
|
||||
# @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, Mh*Mw]
|
||||
q = q * self.scale
|
||||
attn = (q @ k.transpose(-2, -1))
|
||||
|
||||
# relative_position_bias_table.view: [Mh*Mw*Mh*Mw,nH] -> [Mh*Mw,Mh*Mw,nH]
|
||||
relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
|
||||
self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1)
|
||||
relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # [nH, Mh*Mw, Mh*Mw]
|
||||
attn = attn + relative_position_bias.unsqueeze(0)
|
||||
|
||||
if mask is not None:
|
||||
# mask: [nW, Mh*Mw, Mh*Mw]
|
||||
nW = mask.shape[0] # num_windows
|
||||
# attn.view: [batch_size, num_windows, num_heads, Mh*Mw, Mh*Mw]
|
||||
# mask.unsqueeze: [1, nW, 1, Mh*Mw, Mh*Mw]
|
||||
attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
|
||||
attn = attn.view(-1, self.num_heads, N, N)
|
||||
attn = self.softmax(attn)
|
||||
else:
|
||||
attn = self.softmax(attn)
|
||||
|
||||
attn = self.attn_drop(attn)
|
||||
|
||||
# @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
|
||||
# transpose: -> [batch_size*num_windows, Mh*Mw, num_heads, embed_dim_per_head]
|
||||
# reshape: -> [batch_size*num_windows, Mh*Mw, total_embed_dim]
|
||||
x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
|
||||
x = self.proj(x)
|
||||
x = self.proj_drop(x)
|
||||
return x
|
||||
|
||||
class SwinTransformerLayer(nn.Module):
|
||||
# Vision Transformer https://arxiv.org/abs/2010.11929
|
||||
def __init__(self, c, num_heads, window_size=7, shift_size=0,
|
||||
mlp_ratio = 4, qkv_bias=False, drop=0., attn_drop=0., drop_path=0.,
|
||||
act_layer=nn.GELU, norm_layer=nn.LayerNorm):
|
||||
super().__init__()
|
||||
if num_heads > 10:
|
||||
drop_path = 0.1
|
||||
self.window_size = window_size
|
||||
self.shift_size = shift_size
|
||||
self.mlp_ratio = mlp_ratio
|
||||
|
||||
self.norm1 = norm_layer(c)
|
||||
self.attn = WindowAttention(
|
||||
c, window_size=(self.window_size, self.window_size), num_heads=num_heads, qkv_bias=qkv_bias,
|
||||
attn_drop=attn_drop, proj_drop=drop)
|
||||
|
||||
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
|
||||
self.norm2 = norm_layer(c)
|
||||
mlp_hidden_dim = int(c * mlp_ratio)
|
||||
self.mlp = Mlp(in_features=c, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
|
||||
|
||||
def create_mask(self, x, H, W):
|
||||
# calculate attention mask for SW-MSA
|
||||
# 保证Hp和Wp是window_size的整数倍
|
||||
Hp = int(np.ceil(H / self.window_size)) * self.window_size
|
||||
Wp = int(np.ceil(W / self.window_size)) * self.window_size
|
||||
# 拥有和feature map一样的通道排列顺序，方便后续window_partition
|
||||
img_mask = torch.zeros((1, Hp, Wp, 1), device=x.device) # [1, Hp, Wp, 1]
|
||||
h_slices = ( (0, -self.window_size),
|
||||
slice(-self.window_size, -self.shift_size),
|
||||
slice(-self.shift_size, None))
|
||||
w_slices = (slice(0, -self.window_size),
|
||||
slice(-self.window_size, -self.shift_size),
|
||||
slice(-self.shift_size, None))
|
||||
cnt = 0
|
||||
for h in h_slices:
|
||||
for w in w_slices:
|
||||
img_mask[:, h, w, :] = cnt
|
||||
cnt += 1
|
||||
|
||||
mask_windows = window_partition(img_mask, self.window_size) # [nW, Mh, Mw, 1]
|
||||
mask_windows = mask_windows.view(-1, self.window_size * self.window_size) # [nW, Mh*Mw]
|
||||
attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2) # [nW, 1, Mh*Mw] - [nW, Mh*Mw, 1]
|
||||
# [nW, Mh*Mw, Mh*Mw]
|
||||
attn_mask = attn_mask.masked_fill(attn_mask != 0, torch.tensor(-100.0)).masked_fill(attn_mask == 0, torch.tensor(0.0))
|
||||
return attn_mask
|
||||
|
||||
def forward(self, x):
|
||||
b, c, w, h = x.shape
|
||||
x = x.permute(0, 3, 2, 1).contiguous() # [b,h,w,c]
|
||||
|
||||
attn_mask = self.create_mask(x, h, w) # [nW, Mh*Mw, Mh*Mw]
|
||||
shortcut = x
|
||||
x = self.norm1(x)
|
||||
|
||||
pad_l = pad_t = 0
|
||||
pad_r = (self.window_size - w % self.window_size) % self.window_size
|
||||
pad_b = (self.window_size - h % self.window_size) % self.window_size
|
||||
x = F.pad(x, (0, 0, pad_l, pad_r, pad_t, pad_b))
|
||||
_, hp, wp, _ = x.shape
|
||||
|
||||
if self.shift_size > 0:
|
||||
# print(f"shift size: {self.shift_size}")
|
||||
shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
|
||||
else:
|
||||
shifted_x = x
|
||||
attn_mask = None
|
||||
|
||||
x_windows = window_partition(shifted_x, self.window_size) # [nW*B, Mh, Mw, C]
|
||||
x_windows = x_windows.view(-1, self.window_size * self.window_size, c) # [nW*B, Mh*Mw, C]
|
||||
|
||||
attn_windows = self.attn(x_windows, mask=attn_mask) # [nW*B, Mh*Mw, C]
|
||||
|
||||
attn_windows = attn_windows.view(-1, self.window_size, self.window_size, c) # [nW*B, Mh, Mw, C]
|
||||
shifted_x = window_reverse(attn_windows, self.window_size, hp, wp) # [B, H', W', C]
|
||||
|
||||
if self.shift_size > 0:
|
||||
x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
|
||||
else:
|
||||
x = shifted_x
|
||||
|
||||
if pad_r > 0 or pad_b > 0:
|
||||
# 把前面pad的数据移除掉
|
||||
x = x[:, :h, :w, :].contiguous()
|
||||
|
||||
x = shortcut + self.drop_path(x)
|
||||
x = x + self.drop_path(self.mlp(self.norm2(x)))
|
||||
|
||||
x = x.permute(0, 3, 2, 1).contiguous()
|
||||
return x # (b, self.c2, w, h)
|
||||
|
||||
class SwinTransformerBlock(nn.Module):
|
||||
def __init__(self, c1, c2, num_heads, num_layers, window_size=8):
|
||||
super().__init__()
|
||||
self.conv = None
|
||||
if c1 != c2:
|
||||
self.conv = Conv(c1, c2)
|
||||
|
||||
self.window_size = window_size
|
||||
self.shift_size = window_size // 2
|
||||
self.tr = nn.Sequential(*(SwinTransformerLayer(c2, num_heads=num_heads, window_size=window_size, shift_size=0 if (i % 2 == 0) else self.shift_size ) for i in range(num_layers)))
|
||||
|
||||
def forward(self, x):
|
||||
if self.conv is not None:
|
||||
x = self.conv(x)
|
||||
x = self.tr(x)
|
||||
return x
|
||||
|
||||
class Bottleneck(nn.Module):
|
||||
# Standard bottleneck
|
||||
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_, c2, 3, 1, g=g)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
|
||||
|
||||
|
||||
class BottleneckCSP(nn.Module):
|
||||
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
|
||||
self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
|
||||
self.cv4 = Conv(2 * c_, c2, 1, 1)
|
||||
self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3)
|
||||
self.act = nn.SiLU()
|
||||
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
|
||||
|
||||
def forward(self, x):
|
||||
y1 = self.cv3(self.m(self.cv1(x)))
|
||||
y2 = self.cv2(x)
|
||||
return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
|
||||
|
||||
|
||||
class C3(nn.Module):
|
||||
# CSP Bottleneck with 3 convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c1, c_, 1, 1)
|
||||
self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2)
|
||||
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
|
||||
# self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
|
||||
|
||||
def forward(self, x):
|
||||
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
|
||||
|
||||
|
||||
class C3TR(C3):
|
||||
# C3 module with TransformerBlock()
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e)
|
||||
self.m = TransformerBlock(c_, c_, 4, n)
|
||||
|
||||
class C3STR(C3):
|
||||
# C3 module with SwinTransformerBlock()
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e)
|
||||
self.m = SwinTransformerBlock(c_, c_, c_//32, n)
|
||||
|
||||
|
||||
class C3SPP(C3):
|
||||
# C3 module with SPP()
|
||||
def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e)
|
||||
self.m = SPP(c_, c_, k)
|
||||
|
||||
|
||||
class C3Ghost(C3):
|
||||
# C3 module with GhostBottleneck()
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
|
||||
|
||||
|
||||
class SPP(nn.Module):
|
||||
# Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
|
||||
def __init__(self, c1, c2, k=(5, 9, 13)):
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
|
||||
self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
|
||||
|
||||
def forward(self, x):
|
||||
x = self.cv1(x)
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
|
||||
return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
|
||||
|
||||
class ASPP(nn.Module):
|
||||
# Atrous Spatial Pyramid Pooling (ASPP) layer
|
||||
def __init__(self, c1, c2, k=(5, 9, 13)):
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
|
||||
self.m = nn.ModuleList([nn.Conv2d(c_, c_, kernel_size=3, stride=1, padding=(x-1)//2, dilation=(x-1)//2, bias=False) for x in k])
|
||||
self.cv2 = Conv(c_ * (len(k) + 2), c2, 1, 1)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.cv1(x)
|
||||
return self.cv2(torch.cat([x]+ [self.maxpool(x)] + [m(x) for m in self.m] , 1))
|
||||
|
||||
class SPPF(nn.Module):
|
||||
# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
|
||||
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_ * 4, c2, 1, 1)
|
||||
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.cv1(x)
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
|
||||
y1 = self.m(x)
|
||||
y2 = self.m(y1)
|
||||
return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
|
||||
|
||||
|
||||
class Focus(nn.Module):
|
||||
# Focus wh information into c-space
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
|
||||
# self.contract = Contract(gain=2)
|
||||
|
||||
def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2)
|
||||
return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
|
||||
# return self.conv(self.contract(x))
|
||||
|
||||
|
||||
class GhostConv(nn.Module):
|
||||
# Ghost Convolution https://github.com/huawei-noah/ghostnet
|
||||
def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups
|
||||
super().__init__()
|
||||
c_ = c2 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, k, s, None, g, act)
|
||||
self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
|
||||
|
||||
def forward(self, x):
|
||||
y = self.cv1(x)
|
||||
return torch.cat([y, self.cv2(y)], 1)
|
||||
|
||||
|
||||
class GhostBottleneck(nn.Module):
|
||||
# Ghost Bottleneck https://github.com/huawei-noah/ghostnet
|
||||
def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride
|
||||
super().__init__()
|
||||
c_ = c2 // 2
|
||||
self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1), # pw
|
||||
DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw
|
||||
GhostConv(c_, c2, 1, 1, act=False)) # pw-linear
|
||||
self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
|
||||
Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
|
||||
|
||||
def forward(self, x):
|
||||
return self.conv(x) + self.shortcut(x)
|
||||
|
||||
|
||||
class Contract(nn.Module):
|
||||
# Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
b, c, h, w = x.size() # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(b, c, h // s, s, w // s, s) # x(1,64,40,2,40,2)
|
||||
x = x.permute(0, 3, 5, 1, 2, 4).contiguous() # x(1,2,2,64,40,40)
|
||||
return x.view(b, c * s * s, h // s, w // s) # x(1,256,40,40)
|
||||
|
||||
|
||||
class Expand(nn.Module):
|
||||
# Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
b, c, h, w = x.size() # assert C / s ** 2 == 0, 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(b, s, s, c // s ** 2, h, w) # x(1,2,2,16,80,80)
|
||||
x = x.permute(0, 3, 4, 1, 5, 2).contiguous() # x(1,16,80,2,80,2)
|
||||
return x.view(b, c // s ** 2, h * s, w * s) # x(1,16,160,160)
|
||||
|
||||
|
||||
class Concat(nn.Module):
|
||||
# Concatenate a list of tensors along dimension
|
||||
def __init__(self, dimension=1):
|
||||
super().__init__()
|
||||
self.d = dimension
|
||||
|
||||
def forward(self, x):
|
||||
return torch.cat(x, self.d)
|
||||
|
||||
|
||||
class AutoShape(nn.Module):
|
||||
# YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
|
||||
conf = 0.25 # NMS confidence threshold
|
||||
iou = 0.45 # NMS IoU threshold
|
||||
classes = None # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
|
||||
multi_label = False # NMS multiple labels per box
|
||||
max_det = 1000 # maximum number of detections per image
|
||||
|
||||
def __init__(self, model):
|
||||
super().__init__()
|
||||
self.model = model.eval()
|
||||
|
||||
def autoshape(self):
|
||||
LOGGER.info('AutoShape already enabled, skipping... ') # model already converted to model.autoshape()
|
||||
return self
|
||||
|
||||
def _apply(self, fn):
|
||||
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
|
||||
self = super()._apply(fn)
|
||||
m = self.model.model[-1] # Detect()
|
||||
m.stride = fn(m.stride)
|
||||
m.grid = list(map(fn, m.grid))
|
||||
if isinstance(m.anchor_grid, list):
|
||||
m.anchor_grid = list(map(fn, m.anchor_grid))
|
||||
return self
|
||||
|
||||
@torch.no_grad()
|
||||
def forward(self, imgs, size=640, augment=False, profile=False):
|
||||
# Inference from various sources. For height=640, width=1280, RGB images example inputs are:
|
||||
# file: imgs = 'data/images/zidane.jpg' # str or PosixPath
|
||||
# URI: = 'https://ultralytics.com/images/zidane.jpg'
|
||||
# OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3)
|
||||
# PIL: = Image.open('image.jpg') or ImageGrab.grab() # HWC x(640,1280,3)
|
||||
# numpy: = np.zeros((640,1280,3)) # HWC
|
||||
# torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values)
|
||||
# multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
|
||||
|
||||
t = [time_sync()]
|
||||
p = next(self.model.parameters()) # for device and type
|
||||
if isinstance(imgs, torch.Tensor): # torch
|
||||
with amp.autocast(enabled=p.device.type != 'cpu'):
|
||||
return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference
|
||||
|
||||
# Pre-process
|
||||
n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs]) # number of images, list of images
|
||||
shape0, shape1, files = [], [], [] # image and inference shapes, filenames
|
||||
for i, im in enumerate(imgs):
|
||||
f = f'image{i}' # filename
|
||||
if isinstance(im, (str, Path)): # filename or uri
|
||||
im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
|
||||
im = np.asarray(exif_transpose(im))
|
||||
elif isinstance(im, Image.Image): # PIL Image
|
||||
im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
|
||||
files.append(Path(f).with_suffix('.jpg').name)
|
||||
if im.shape[0] < 5: # image in CHW
|
||||
im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
|
||||
im = im[..., :3] if im.ndim == 3 else np.tile(im[..., None], 3) # enforce 3ch input
|
||||
s = im.shape[:2] # HWC
|
||||
shape0.append(s) # image shape
|
||||
g = (size / max(s)) # gain
|
||||
shape1.append([y * g for y in s])
|
||||
imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update
|
||||
shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)] # inference shape
|
||||
x = [letterbox(im, new_shape=shape1, auto=False)[0] for im in imgs] # pad
|
||||
x = np.stack(x, 0) if n > 1 else x[0][None] # stack
|
||||
x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW
|
||||
x = torch.from_numpy(x).to(p.device).type_as(p) / 255 # uint8 to fp16/32
|
||||
t.append(time_sync())
|
||||
|
||||
with amp.autocast(enabled=p.device.type != 'cpu'):
|
||||
# Inference
|
||||
y = self.model(x, augment, profile)[0] # forward
|
||||
t.append(time_sync())
|
||||
|
||||
# Post-process
|
||||
y = non_max_suppression(y, self.conf, iou_thres=self.iou, classes=self.classes,
|
||||
multi_label=self.multi_label, max_det=self.max_det) # NMS
|
||||
for i in range(n):
|
||||
scale_coords(shape1, y[i][:, :4], shape0[i])
|
||||
|
||||
t.append(time_sync())
|
||||
return Detections(imgs, y, files, t, self.names, x.shape)
|
||||
|
||||
|
||||
class Detections:
|
||||
# YOLOv5 detections class for inference results
|
||||
def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
|
||||
super().__init__()
|
||||
d = pred[0].device # device
|
||||
gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in imgs] # normalizations
|
||||
self.imgs = imgs # list of images as numpy arrays
|
||||
self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
|
||||
self.names = names # class names
|
||||
self.files = files # image filenames
|
||||
self.xyxy = pred # xyxy pixels
|
||||
self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
|
||||
self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
|
||||
self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
|
||||
self.n = len(self.pred) # number of images (batch size)
|
||||
self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms)
|
||||
self.s = shape # inference BCHW shape
|
||||
|
||||
def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
|
||||
crops = []
|
||||
for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
|
||||
s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
|
||||
if pred.shape[0]:
|
||||
for c in pred[:, -1].unique():
|
||||
n = (pred[:, -1] == c).sum() # detections per class
|
||||
s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
|
||||
if show or save or render or crop:
|
||||
annotator = Annotator(im, example=str(self.names))
|
||||
for *box, conf, cls in reversed(pred): # xyxy, confidence, class
|
||||
label = f'{self.names[int(cls)]} {conf:.2f}'
|
||||
if crop:
|
||||
file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
|
||||
crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label,
|
||||
'im': save_one_box(box, im, file=file, save=save)})
|
||||
else: # all others
|
||||
annotator.box_label(box, label, color=colors(cls))
|
||||
im = annotator.im
|
||||
else:
|
||||
s += '(no detections)'
|
||||
|
||||
im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np
|
||||
if pprint:
|
||||
LOGGER.info(s.rstrip(', '))
|
||||
if show:
|
||||
im.show(self.files[i]) # show
|
||||
if save:
|
||||
f = self.files[i]
|
||||
im.save(save_dir / f) # save
|
||||
if i == self.n - 1:
|
||||
LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
|
||||
if render:
|
||||
self.imgs[i] = np.asarray(im)
|
||||
if crop:
|
||||
if save:
|
||||
LOGGER.info(f'Saved results to {save_dir}\n')
|
||||
return crops
|
||||
|
||||
def print(self):
|
||||
self.display(pprint=True) # print results
|
||||
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' %
|
||||
self.t)
|
||||
|
||||
def show(self):
|
||||
self.display(show=True) # show results
|
||||
|
||||
def save(self, save_dir='runs/detect/exp'):
|
||||
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) # increment save_dir
|
||||
self.display(save=True, save_dir=save_dir) # save results
|
||||
|
||||
def crop(self, save=True, save_dir='runs/detect/exp'):
|
||||
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
|
||||
return self.display(crop=True, save=save, save_dir=save_dir) # crop results
|
||||
|
||||
def render(self):
|
||||
self.display(render=True) # render results
|
||||
return self.imgs
|
||||
|
||||
def pandas(self):
|
||||
# return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
|
||||
new = copy(self) # return copy
|
||||
ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns
|
||||
cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns
|
||||
for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
|
||||
a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update
|
||||
setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
|
||||
return new
|
||||
|
||||
def tolist(self):
|
||||
# return a list of Detections objects, i.e. 'for result in results.tolist():'
|
||||
x = [Detections([self.imgs[i]], [self.pred[i]], self.names, self.s) for i in range(self.n)]
|
||||
for d in x:
|
||||
for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
|
||||
setattr(d, k, getattr(d, k)[0]) # pop out of list
|
||||
return x
|
||||
|
||||
def __len__(self):
|
||||
return self.n
|
||||
|
||||
|
||||
class Classify(nn.Module):
|
||||
# Classification head, i.e. x(b,c1,20,20) to x(b,c2)
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.aap = nn.AdaptiveAvgPool2d(1) # to x(b,c1,1,1)
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g) # to x(b,c2,1,1)
|
||||
self.flat = nn.Flatten()
|
||||
|
||||
def forward(self, x):
|
||||
z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1) # cat if list
|
||||
return self.flat(self.conv(z)) # flatten to x(b,c2)
|
||||
|
|
@ -0,0 +1,120 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Experimental modules
|
||||
"""
|
||||
import math
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
from models.common import Conv
|
||||
from utils.downloads import attempt_download
|
||||
|
||||
|
||||
class CrossConv(nn.Module):
|
||||
# Cross Convolution Downsample
|
||||
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
|
||||
# ch_in, ch_out, kernel, stride, groups, expansion, shortcut
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, (1, k), (1, s))
|
||||
self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
|
||||
|
||||
|
||||
class Sum(nn.Module):
|
||||
# Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
|
||||
def __init__(self, n, weight=False): # n: number of inputs
|
||||
super().__init__()
|
||||
self.weight = weight # apply weights boolean
|
||||
self.iter = range(n - 1) # iter object
|
||||
if weight:
|
||||
self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True) # layer weights
|
||||
|
||||
def forward(self, x):
|
||||
y = x[0] # no weight
|
||||
if self.weight:
|
||||
w = torch.sigmoid(self.w) * 2
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1] * w[i]
|
||||
else:
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1]
|
||||
return y
|
||||
|
||||
|
||||
class MixConv2d(nn.Module):
|
||||
# Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
|
||||
def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True): # ch_in, ch_out, kernel, stride, ch_strategy
|
||||
super().__init__()
|
||||
n = len(k) # number of convolutions
|
||||
if equal_ch: # equal c_ per group
|
||||
i = torch.linspace(0, n - 1E-6, c2).floor() # c2 indices
|
||||
c_ = [(i == g).sum() for g in range(n)] # intermediate channels
|
||||
else: # equal weight.numel() per group
|
||||
b = [c2] + [0] * n
|
||||
a = np.eye(n + 1, n, k=-1)
|
||||
a -= np.roll(a, 1, axis=1)
|
||||
a *= np.array(k) ** 2
|
||||
a[0] = 1
|
||||
c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
|
||||
|
||||
self.m = nn.ModuleList(
|
||||
[nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)])
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.SiLU()
|
||||
|
||||
def forward(self, x):
|
||||
return self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
|
||||
|
||||
|
||||
class Ensemble(nn.ModuleList):
|
||||
# Ensemble of models
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
|
||||
def forward(self, x, augment=False, profile=False, visualize=False):
|
||||
y = []
|
||||
for module in self:
|
||||
y.append(module(x, augment, profile, visualize)[0])
|
||||
# y = torch.stack(y).max(0)[0] # max ensemble
|
||||
# y = torch.stack(y).mean(0) # mean ensemble
|
||||
y = torch.cat(y, 1) # nms ensemble
|
||||
return y, None # inference, train output
|
||||
|
||||
|
||||
def attempt_load(weights, map_location=None, inplace=True, fuse=True):
|
||||
from models.yolo import Detect, Model
|
||||
|
||||
# Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
|
||||
model = Ensemble()
|
||||
for w in weights if isinstance(weights, list) else [weights]:
|
||||
ckpt = torch.load(attempt_download(w), map_location=map_location) # load
|
||||
if fuse:
|
||||
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
|
||||
else:
|
||||
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval()) # without layer fuse
|
||||
|
||||
# Compatibility updates
|
||||
for m in model.modules():
|
||||
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]:
|
||||
m.inplace = inplace # pytorch 1.7.0 compatibility
|
||||
if type(m) is Detect:
|
||||
if not isinstance(m.anchor_grid, list): # new Detect Layer compatibility
|
||||
delattr(m, 'anchor_grid')
|
||||
setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
|
||||
elif type(m) is Conv:
|
||||
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
|
||||
|
||||
if len(model) == 1:
|
||||
return model[-1] # return model
|
||||
else:
|
||||
print(f'Ensemble created with {weights}\n')
|
||||
for k in ['names']:
|
||||
setattr(model, k, getattr(model[-1], k))
|
||||
model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride
|
||||
return model # return ensemble
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Default anchors for COCO data
|
||||
|
||||
|
||||
# P5 -------------------------------------------------------------------------------------------------------------------
|
||||
# P5-640:
|
||||
anchors_p5_640:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
|
||||
# P6 -------------------------------------------------------------------------------------------------------------------
|
||||
# P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387
|
||||
anchors_p6_640:
|
||||
- [9,11, 21,19, 17,41] # P3/8
|
||||
- [43,32, 39,70, 86,64] # P4/16
|
||||
- [65,131, 134,130, 120,265] # P5/32
|
||||
- [282,180, 247,354, 512,387] # P6/64
|
||||
|
||||
# P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792
|
||||
anchors_p6_1280:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187
|
||||
anchors_p6_1920:
|
||||
- [28,41, 67,59, 57,141] # P3/8
|
||||
- [144,103, 129,227, 270,205] # P4/16
|
||||
- [209,452, 455,396, 358,812] # P5/32
|
||||
- [653,922, 1109,570, 1387,1187] # P6/64
|
||||
|
||||
|
||||
# P7 -------------------------------------------------------------------------------------------------------------------
|
||||
# P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372
|
||||
anchors_p7_640:
|
||||
- [11,11, 13,30, 29,20] # P3/8
|
||||
- [30,46, 61,38, 39,92] # P4/16
|
||||
- [78,80, 146,66, 79,163] # P5/32
|
||||
- [149,150, 321,143, 157,303] # P6/64
|
||||
- [257,402, 359,290, 524,372] # P7/128
|
||||
|
||||
# P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818
|
||||
anchors_p7_1280:
|
||||
- [19,22, 54,36, 32,77] # P3/8
|
||||
- [70,83, 138,71, 75,173] # P4/16
|
||||
- [165,159, 148,334, 375,151] # P5/32
|
||||
- [334,317, 251,626, 499,474] # P6/64
|
||||
- [750,326, 534,814, 1079,818] # P7/128
|
||||
|
||||
# P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227
|
||||
anchors_p7_1920:
|
||||
- [29,34, 81,55, 47,115] # P3/8
|
||||
- [105,124, 207,107, 113,259] # P4/16
|
||||
- [247,238, 222,500, 563,227] # P5/32
|
||||
- [501,476, 376,939, 749,711] # P6/64
|
||||
- [1126,489, 801,1222, 1618,1227] # P7/128
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3-SPP head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, SPP, [512, [5, 9, 13]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,14, 23,27, 37,58] # P4/16
|
||||
- [81,82, 135,169, 344,319] # P5/32
|
||||
|
||||
# YOLOv3-tiny backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [16, 3, 1]], # 0
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2
|
||||
[-1, 1, Conv, [32, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11
|
||||
[-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12
|
||||
]
|
||||
|
||||
# YOLOv3-tiny head
|
||||
head:
|
||||
[[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium)
|
||||
|
||||
[[19, 15], 1, Detect, [nc, anchors]], # Detect(P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3 head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, Conv, [512, [1, 1]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 BiFPN head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14, 6], 1, Concat, [1]], # cat P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 6, BottleneckCSP, [1024]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 FPN head
|
||||
head:
|
||||
[[-1, 3, BottleneckCSP, [1024, False]], # 10 (P5/32-large)
|
||||
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 14 (P4/16-medium)
|
||||
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 3, BottleneckCSP, [256, False]], # 18 (P3/8-small)
|
||||
|
||||
[[18, 14, 10], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,54 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 2], 1, Concat, [1]], # cat backbone P2
|
||||
[-1, 1, C3, [128, False]], # 21 (P2/4-xsmall)
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2]],
|
||||
[[-1, 18], 1, Concat, [1]], # cat head P3
|
||||
[-1, 3, C3, [256, False]], # 24 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 27 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 30 (P5/32-large)
|
||||
|
||||
[[21, 24, 27, 30], 1, Detect, [nc, anchors]], # Detect(P2, P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 1, SPP, [1024, [3, 5, 7]]],
|
||||
[-1, 3, C3, [1024, False]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P5/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,67 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, Conv, [1280, 3, 2]], # 11-P7/128
|
||||
[-1, 1, SPP, [1280, [3, 5]]],
|
||||
[-1, 3, C3, [1280, False]], # 13
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [1024, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 10], 1, Concat, [1]], # cat backbone P6
|
||||
[-1, 3, C3, [1024, False]], # 17
|
||||
|
||||
[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 21
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 25
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 29 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 26], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 32 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 22], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 35 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 18], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 38 (P6/64-xlarge)
|
||||
|
||||
[-1, 1, Conv, [1024, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P7
|
||||
[-1, 3, C3, [1280, False]], # 41 (P7/128-xxlarge)
|
||||
|
||||
[[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6, P7)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, BottleneckCSP, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 PANet head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, BottleneckCSP, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.67 # model depth multiple
|
||||
width_multiple: 0.75 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.25 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, GhostConv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3Ghost, [128]],
|
||||
[-1, 1, GhostConv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3Ghost, [256]],
|
||||
[-1, 1, GhostConv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3Ghost, [512]],
|
||||
[-1, 1, GhostConv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3Ghost, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, GhostConv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3Ghost, [512, False]], # 13
|
||||
|
||||
[-1, 1, GhostConv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3Ghost, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, GhostConv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3Ghost, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, GhostConv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3Ghost, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3TR, [1024, False]], # 9 <-------- C3TR() Transformer module
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.33 # model depth multiple
|
||||
width_multiple: 1.25 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,465 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
TensorFlow, Keras and TFLite versions of YOLOv5
|
||||
Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
|
||||
|
||||
Usage:
|
||||
$ python models/tf.py --weights yolov5s.pt
|
||||
|
||||
Export:
|
||||
$ python path/to/export.py --weights yolov5s.pt --include saved_model pb tflite tfjs
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import sys
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
# ROOT = ROOT.relative_to(Path.cwd()) # relative
|
||||
|
||||
import numpy as np
|
||||
import tensorflow as tf
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from tensorflow import keras
|
||||
|
||||
from models.common import C3, SPP, SPPF, Bottleneck, BottleneckCSP, Concat, Conv, DWConv, Focus, autopad
|
||||
from models.experimental import CrossConv, MixConv2d, attempt_load
|
||||
from models.yolo import Detect
|
||||
from utils.activations import SiLU
|
||||
from utils.general import LOGGER, make_divisible, print_args
|
||||
|
||||
|
||||
class TFBN(keras.layers.Layer):
|
||||
# TensorFlow BatchNormalization wrapper
|
||||
def __init__(self, w=None):
|
||||
super().__init__()
|
||||
self.bn = keras.layers.BatchNormalization(
|
||||
beta_initializer=keras.initializers.Constant(w.bias.numpy()),
|
||||
gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
|
||||
moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
|
||||
moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
|
||||
epsilon=w.eps)
|
||||
|
||||
def call(self, inputs):
|
||||
return self.bn(inputs)
|
||||
|
||||
|
||||
class TFPad(keras.layers.Layer):
|
||||
def __init__(self, pad):
|
||||
super().__init__()
|
||||
self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
|
||||
|
||||
def call(self, inputs):
|
||||
return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
|
||||
|
||||
|
||||
class TFConv(keras.layers.Layer):
|
||||
# Standard convolution
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
|
||||
# ch_in, ch_out, weights, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
|
||||
assert isinstance(k, int), "Convolution with multiple kernels are not allowed."
|
||||
# TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
|
||||
# see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
|
||||
|
||||
conv = keras.layers.Conv2D(
|
||||
c2, k, s, 'SAME' if s == 1 else 'VALID', use_bias=False if hasattr(w, 'bn') else True,
|
||||
kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
|
||||
bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
|
||||
self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
|
||||
self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
|
||||
|
||||
# YOLOv5 activations
|
||||
if isinstance(w.act, nn.LeakyReLU):
|
||||
self.act = (lambda x: keras.activations.relu(x, alpha=0.1)) if act else tf.identity
|
||||
elif isinstance(w.act, nn.Hardswish):
|
||||
self.act = (lambda x: x * tf.nn.relu6(x + 3) * 0.166666667) if act else tf.identity
|
||||
elif isinstance(w.act, (nn.SiLU, SiLU)):
|
||||
self.act = (lambda x: keras.activations.swish(x)) if act else tf.identity
|
||||
else:
|
||||
raise Exception(f'no matching TensorFlow activation found for {w.act}')
|
||||
|
||||
def call(self, inputs):
|
||||
return self.act(self.bn(self.conv(inputs)))
|
||||
|
||||
|
||||
class TFFocus(keras.layers.Layer):
|
||||
# Focus wh information into c-space
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
|
||||
# ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
|
||||
|
||||
def call(self, inputs): # x(b,w,h,c) -> y(b,w/2,h/2,4c)
|
||||
# inputs = inputs / 255 # normalize 0-255 to 0-1
|
||||
return self.conv(tf.concat([inputs[:, ::2, ::2, :],
|
||||
inputs[:, 1::2, ::2, :],
|
||||
inputs[:, ::2, 1::2, :],
|
||||
inputs[:, 1::2, 1::2, :]], 3))
|
||||
|
||||
|
||||
class TFBottleneck(keras.layers.Layer):
|
||||
# Standard bottleneck
|
||||
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None): # ch_in, ch_out, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def call(self, inputs):
|
||||
return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
|
||||
|
||||
|
||||
class TFConv2d(keras.layers.Layer):
|
||||
# Substitution for PyTorch nn.Conv2D
|
||||
def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
|
||||
super().__init__()
|
||||
assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
|
||||
self.conv = keras.layers.Conv2D(
|
||||
c2, k, s, 'VALID', use_bias=bias,
|
||||
kernel_initializer=keras.initializers.Constant(w.weight.permute(2, 3, 1, 0).numpy()),
|
||||
bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None, )
|
||||
|
||||
def call(self, inputs):
|
||||
return self.conv(inputs)
|
||||
|
||||
|
||||
class TFBottleneckCSP(keras.layers.Layer):
|
||||
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
|
||||
# ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
|
||||
self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
|
||||
self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
|
||||
self.bn = TFBN(w.bn)
|
||||
self.act = lambda x: keras.activations.relu(x, alpha=0.1)
|
||||
self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
|
||||
|
||||
def call(self, inputs):
|
||||
y1 = self.cv3(self.m(self.cv1(inputs)))
|
||||
y2 = self.cv2(inputs)
|
||||
return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
|
||||
|
||||
|
||||
class TFC3(keras.layers.Layer):
|
||||
# CSP Bottleneck with 3 convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
|
||||
# ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
|
||||
self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
|
||||
self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
|
||||
|
||||
def call(self, inputs):
|
||||
return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
|
||||
|
||||
|
||||
class TFSPP(keras.layers.Layer):
|
||||
# Spatial pyramid pooling layer used in YOLOv3-SPP
|
||||
def __init__(self, c1, c2, k=(5, 9, 13), w=None):
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
|
||||
self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
|
||||
|
||||
def call(self, inputs):
|
||||
x = self.cv1(inputs)
|
||||
return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
|
||||
|
||||
|
||||
class TFSPPF(keras.layers.Layer):
|
||||
# Spatial pyramid pooling-Fast layer
|
||||
def __init__(self, c1, c2, k=5, w=None):
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
|
||||
self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
|
||||
|
||||
def call(self, inputs):
|
||||
x = self.cv1(inputs)
|
||||
y1 = self.m(x)
|
||||
y2 = self.m(y1)
|
||||
return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
|
||||
|
||||
|
||||
class TFDetect(keras.layers.Layer):
|
||||
def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None): # detection layer
|
||||
super().__init__()
|
||||
self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [tf.zeros(1)] * self.nl # init grid
|
||||
self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
|
||||
self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]),
|
||||
[self.nl, 1, -1, 1, 2])
|
||||
self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
|
||||
self.training = False # set to False after building model
|
||||
self.imgsz = imgsz
|
||||
for i in range(self.nl):
|
||||
ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
|
||||
self.grid[i] = self._make_grid(nx, ny)
|
||||
|
||||
def call(self, inputs):
|
||||
z = [] # inference output
|
||||
x = []
|
||||
for i in range(self.nl):
|
||||
x.append(self.m[i](inputs[i]))
|
||||
# x(bs,20,20,255) to x(bs,3,20,20,85)
|
||||
ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
|
||||
x[i] = tf.transpose(tf.reshape(x[i], [-1, ny * nx, self.na, self.no]), [0, 2, 1, 3])
|
||||
|
||||
if not self.training: # inference
|
||||
y = tf.sigmoid(x[i])
|
||||
xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
|
||||
# Normalize xywh to 0-1 to reduce calibration error
|
||||
xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
|
||||
wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
|
||||
y = tf.concat([xy, wh, y[..., 4:]], -1)
|
||||
z.append(tf.reshape(y, [-1, 3 * ny * nx, self.no]))
|
||||
|
||||
return x if self.training else (tf.concat(z, 1), x)
|
||||
|
||||
@staticmethod
|
||||
def _make_grid(nx=20, ny=20):
|
||||
# yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||||
# return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||||
xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
|
||||
return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
|
||||
|
||||
|
||||
class TFUpsample(keras.layers.Layer):
|
||||
def __init__(self, size, scale_factor, mode, w=None): # warning: all arguments needed including 'w'
|
||||
super().__init__()
|
||||
assert scale_factor == 2, "scale_factor must be 2"
|
||||
self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
|
||||
# self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
|
||||
# with default arguments: align_corners=False, half_pixel_centers=False
|
||||
# self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
|
||||
# size=(x.shape[1] * 2, x.shape[2] * 2))
|
||||
|
||||
def call(self, inputs):
|
||||
return self.upsample(inputs)
|
||||
|
||||
|
||||
class TFConcat(keras.layers.Layer):
|
||||
def __init__(self, dimension=1, w=None):
|
||||
super().__init__()
|
||||
assert dimension == 1, "convert only NCHW to NHWC concat"
|
||||
self.d = 3
|
||||
|
||||
def call(self, inputs):
|
||||
return tf.concat(inputs, self.d)
|
||||
|
||||
|
||||
def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
|
||||
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
|
||||
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
|
||||
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
|
||||
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
|
||||
|
||||
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
|
||||
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
|
||||
m_str = m
|
||||
m = eval(m) if isinstance(m, str) else m # eval strings
|
||||
for j, a in enumerate(args):
|
||||
try:
|
||||
args[j] = eval(a) if isinstance(a, str) else a # eval strings
|
||||
except NameError:
|
||||
pass
|
||||
|
||||
n = max(round(n * gd), 1) if n > 1 else n # depth gain
|
||||
if m in [nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3]:
|
||||
c1, c2 = ch[f], args[0]
|
||||
c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
|
||||
|
||||
args = [c1, c2, *args[1:]]
|
||||
if m in [BottleneckCSP, C3]:
|
||||
args.insert(2, n)
|
||||
n = 1
|
||||
elif m is nn.BatchNorm2d:
|
||||
args = [ch[f]]
|
||||
elif m is Concat:
|
||||
c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
|
||||
elif m is Detect:
|
||||
args.append([ch[x + 1] for x in f])
|
||||
if isinstance(args[1], int): # number of anchors
|
||||
args[1] = [list(range(args[1] * 2))] * len(f)
|
||||
args.append(imgsz)
|
||||
else:
|
||||
c2 = ch[f]
|
||||
|
||||
tf_m = eval('TF' + m_str.replace('nn.', ''))
|
||||
m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
|
||||
else tf_m(*args, w=model.model[i]) # module
|
||||
|
||||
torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
|
||||
t = str(m)[8:-2].replace('__main__.', '') # module type
|
||||
np = sum(x.numel() for x in torch_m_.parameters()) # number params
|
||||
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
|
||||
LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10} {t:<40}{str(args):<30}') # print
|
||||
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
|
||||
layers.append(m_)
|
||||
ch.append(c2)
|
||||
return keras.Sequential(layers), sorted(save)
|
||||
|
||||
|
||||
class TFModel:
|
||||
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)): # model, channels, classes
|
||||
super().__init__()
|
||||
if isinstance(cfg, dict):
|
||||
self.yaml = cfg # model dict
|
||||
else: # is *.yaml
|
||||
import yaml # for torch hub
|
||||
self.yaml_file = Path(cfg).name
|
||||
with open(cfg) as f:
|
||||
self.yaml = yaml.load(f, Loader=yaml.FullLoader) # model dict
|
||||
|
||||
# Define model
|
||||
if nc and nc != self.yaml['nc']:
|
||||
LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
|
||||
self.yaml['nc'] = nc # override yaml value
|
||||
self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
|
||||
|
||||
def predict(self, inputs, tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
|
||||
conf_thres=0.25):
|
||||
y = [] # outputs
|
||||
x = inputs
|
||||
for i, m in enumerate(self.model.layers):
|
||||
if m.f != -1: # if not from previous layer
|
||||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
|
||||
|
||||
x = m(x) # run
|
||||
y.append(x if m.i in self.savelist else None) # save output
|
||||
|
||||
# Add TensorFlow NMS
|
||||
if tf_nms:
|
||||
boxes = self._xywh2xyxy(x[0][..., :4])
|
||||
probs = x[0][:, :, 4:5]
|
||||
classes = x[0][:, :, 5:]
|
||||
scores = probs * classes
|
||||
if agnostic_nms:
|
||||
nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
|
||||
return nms, x[1]
|
||||
else:
|
||||
boxes = tf.expand_dims(boxes, 2)
|
||||
nms = tf.image.combined_non_max_suppression(
|
||||
boxes, scores, topk_per_class, topk_all, iou_thres, conf_thres, clip_boxes=False)
|
||||
return nms, x[1]
|
||||
|
||||
return x[0] # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...]
|
||||
# x = x[0][0] # [x(1,6300,85), ...] to x(6300,85)
|
||||
# xywh = x[..., :4] # x(6300,4) boxes
|
||||
# conf = x[..., 4:5] # x(6300,1) confidences
|
||||
# cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1)) # x(6300,1) classes
|
||||
# return tf.concat([conf, cls, xywh], 1)
|
||||
|
||||
@staticmethod
|
||||
def _xywh2xyxy(xywh):
|
||||
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
|
||||
x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
|
||||
return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
|
||||
|
||||
|
||||
class AgnosticNMS(keras.layers.Layer):
|
||||
# TF Agnostic NMS
|
||||
def call(self, input, topk_all, iou_thres, conf_thres):
|
||||
# wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
|
||||
return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres), input,
|
||||
fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
|
||||
name='agnostic_nms')
|
||||
|
||||
@staticmethod
|
||||
def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25): # agnostic NMS
|
||||
boxes, classes, scores = x
|
||||
class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
|
||||
scores_inp = tf.reduce_max(scores, -1)
|
||||
selected_inds = tf.image.non_max_suppression(
|
||||
boxes, scores_inp, max_output_size=topk_all, iou_threshold=iou_thres, score_threshold=conf_thres)
|
||||
selected_boxes = tf.gather(boxes, selected_inds)
|
||||
padded_boxes = tf.pad(selected_boxes,
|
||||
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
|
||||
mode="CONSTANT", constant_values=0.0)
|
||||
selected_scores = tf.gather(scores_inp, selected_inds)
|
||||
padded_scores = tf.pad(selected_scores,
|
||||
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
|
||||
mode="CONSTANT", constant_values=-1.0)
|
||||
selected_classes = tf.gather(class_inds, selected_inds)
|
||||
padded_classes = tf.pad(selected_classes,
|
||||
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
|
||||
mode="CONSTANT", constant_values=-1.0)
|
||||
valid_detections = tf.shape(selected_inds)[0]
|
||||
return padded_boxes, padded_scores, padded_classes, valid_detections
|
||||
|
||||
|
||||
def representative_dataset_gen(dataset, ncalib=100):
|
||||
# Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
|
||||
for n, (path, img, im0s, vid_cap, string) in enumerate(dataset):
|
||||
input = np.transpose(img, [1, 2, 0])
|
||||
input = np.expand_dims(input, axis=0).astype(np.float32)
|
||||
input /= 255
|
||||
yield [input]
|
||||
if n >= ncalib:
|
||||
break
|
||||
|
||||
|
||||
def run(weights=ROOT / 'yolov5s.pt', # weights path
|
||||
imgsz=(640, 640), # inference size h,w
|
||||
batch_size=1, # batch size
|
||||
dynamic=False, # dynamic batch size
|
||||
):
|
||||
# PyTorch model
|
||||
im = torch.zeros((batch_size, 3, *imgsz)) # BCHW image
|
||||
model = attempt_load(weights, map_location=torch.device('cpu'), inplace=True, fuse=False)
|
||||
y = model(im) # inference
|
||||
model.info()
|
||||
|
||||
# TensorFlow model
|
||||
im = tf.zeros((batch_size, *imgsz, 3)) # BHWC image
|
||||
tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
|
||||
y = tf_model.predict(im) # inference
|
||||
|
||||
# Keras model
|
||||
im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
|
||||
keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
|
||||
keras_model.summary()
|
||||
|
||||
LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
|
||||
|
||||
|
||||
def parse_opt():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
|
||||
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
|
||||
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
|
||||
parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
|
||||
opt = parser.parse_args()
|
||||
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
|
||||
print_args(FILE.stem, opt)
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
|
|
@ -0,0 +1,474 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
YOLO-specific modules
|
||||
|
||||
Usage:
|
||||
$ python path/to/models/yolo.py --cfg yolov5s.yaml
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import sys
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
# ROOT = ROOT.relative_to(Path.cwd()) # relative
|
||||
|
||||
from models.common import *
|
||||
from models.experimental import *
|
||||
from utils.autoanchor import check_anchor_order
|
||||
from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
|
||||
from utils.plots import feature_visualization
|
||||
from utils.torch_utils import (copy_attr, fuse_conv_and_bn, initialize_weights, model_info, scale_img, select_device,
|
||||
time_sync)
|
||||
|
||||
try:
|
||||
import thop # for FLOPs computation
|
||||
except ImportError:
|
||||
thop = None
|
||||
|
||||
|
||||
class Detect(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
onnx_dynamic = False # ONNX export parameter
|
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
|
||||
super().__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
self.anchor_grid = [torch.zeros(1)] * self.nl # init anchor grid
|
||||
self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
|
||||
self.inplace = inplace # use in-place ops (e.g. slice assignment)
|
||||
|
||||
def forward(self, x):
|
||||
z = [] # inference output
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](x[i]) # conv
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
||||
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
|
||||
|
||||
y = x[i].sigmoid()
|
||||
if self.inplace:
|
||||
y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
|
||||
xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
y = torch.cat((xy, wh, y[..., 4:]), -1)
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
return x if self.training else (torch.cat(z, 1), x)
|
||||
# return x if self.training else (z[0], x) # (torch.cat(z, 1), x)
|
||||
|
||||
def _make_grid(self, nx=20, ny=20, i=0):
|
||||
d = self.anchors[i].device
|
||||
if check_version(torch.__version__, '1.10.0'): # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
|
||||
yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)], indexing='ij')
|
||||
else:
|
||||
yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])
|
||||
grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
|
||||
anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
|
||||
.view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
|
||||
return grid, anchor_grid
|
||||
|
||||
class CLLA(nn.Module):
|
||||
def __init__(self, range, c):
|
||||
super().__init__()
|
||||
self.c_ = c
|
||||
self.q = nn.Linear(self.c_, self.c_)
|
||||
self.k = nn.Linear(self.c_, self.c_)
|
||||
self.v = nn.Linear(self.c_, self.c_)
|
||||
self.range = range
|
||||
self.attend = nn.Softmax(dim = -1)
|
||||
|
||||
def forward(self, x1, x2):
|
||||
b1, c1, w1, h1 = x1.shape
|
||||
b2, c2, w2, h2 = x2.shape
|
||||
assert b1 == b2 and c1 == c2
|
||||
|
||||
x2_ = x2.permute(0, 2, 3, 1).contiguous().unsqueeze(3)
|
||||
pad = int(self.range / 2 - 1)
|
||||
padding = nn.ZeroPad2d(padding=(pad, pad, pad, pad))
|
||||
x1 = padding(x1)
|
||||
|
||||
local = []
|
||||
for i in range(int(self.range)):
|
||||
for j in range(int(self.range)):
|
||||
tem = x1
|
||||
tem = tem[..., i::2, j::2][..., :w2, :h2].contiguous().unsqueeze(2)
|
||||
local.append(tem)
|
||||
local = torch.cat(local, 2)
|
||||
|
||||
x1 = local.permute(0, 3, 4, 2, 1)
|
||||
|
||||
q = self.q(x2_)
|
||||
k, v = self.k(x1), self.v(x1)
|
||||
|
||||
dots = torch.sum(q * k / self.range, 4)
|
||||
irr = torch.mean(dots, 3).unsqueeze(3) * 2 - dots
|
||||
att = self.attend(irr)
|
||||
|
||||
out = v * att.unsqueeze(4)
|
||||
out = torch.sum(out, 3)
|
||||
out = out.squeeze(3).permute(0, 3, 1, 2).contiguous()
|
||||
# x2 = x2.squeeze(3).permute(0, 3, 1, 2).contiguous()
|
||||
return (out + x2) / 2
|
||||
# return out
|
||||
|
||||
class CLLABlock(nn.Module):
|
||||
def __init__(self, range=2, ch=256, ch1=128, ch2=256, out=0):
|
||||
super().__init__()
|
||||
self.range = range
|
||||
self.c_ = ch
|
||||
self.cout = out
|
||||
self.conv1 = nn.Conv2d(ch1, self.c_, 1)
|
||||
self.conv2 = nn.Conv2d(ch2, self.c_, 1)
|
||||
|
||||
self.att = CLLA(range = range, c = self.c_)
|
||||
|
||||
self.det = nn.Conv2d(self.c_, out, 1)
|
||||
|
||||
def forward(self, x1, x2):
|
||||
x1 = self.conv1(x1)
|
||||
x2 = self.conv2(x2)
|
||||
|
||||
f = self.att(x1, x2)
|
||||
|
||||
return self.det(f)
|
||||
|
||||
|
||||
class CLLADetect(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
onnx_dynamic = False # ONNX export parameter
|
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
|
||||
super().__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
self.anchor_grid = [torch.zeros(1)] * self.nl # init anchor grid
|
||||
self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)
|
||||
self.det = CLLABlock(range = 2, ch = ch[0], ch1 = ch[0], ch2 = ch[1], out = self.no * self.na)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch[2:]) # output conv
|
||||
self.inplace = inplace # use in-place ops (e.g. slice assignment)
|
||||
|
||||
def forward(self, x):
|
||||
z = [] # inference output
|
||||
p = []
|
||||
for i in range(self.nl):
|
||||
if i == 0:
|
||||
p.append(self.det(x[0], x[1]))
|
||||
else:
|
||||
p.append(self.m[i-1](x[i+1])) # conv
|
||||
bs, _, ny, nx = p[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
|
||||
p[i] = p[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.onnx_dynamic or self.grid[i].shape[2:4] != p[i].shape[2:4]:
|
||||
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
|
||||
|
||||
y = p[i].sigmoid()
|
||||
if self.inplace:
|
||||
y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
|
||||
xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
y = torch.cat((xy, wh, y[..., 4:]), -1)
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
return p if self.training else (torch.cat(z, 1), p)
|
||||
# return x if self.training else (z[0], x) # (torch.cat(z, 1), x)
|
||||
|
||||
def _make_grid(self, nx=20, ny=20, i=0):
|
||||
d = self.anchors[i].device
|
||||
if check_version(torch.__version__, '1.10.0'): # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
|
||||
yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)], indexing='ij')
|
||||
else:
|
||||
yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])
|
||||
grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
|
||||
anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
|
||||
.view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
|
||||
return grid, anchor_grid
|
||||
|
||||
class Model(nn.Module):
|
||||
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
|
||||
super().__init__()
|
||||
if isinstance(cfg, dict):
|
||||
self.yaml = cfg # model dict
|
||||
else: # is *.yaml
|
||||
import yaml # for torch hub
|
||||
self.yaml_file = Path(cfg).name
|
||||
with open(cfg, errors='ignore') as f:
|
||||
self.yaml = yaml.safe_load(f) # model dict
|
||||
|
||||
# Define model
|
||||
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
|
||||
if nc and nc != self.yaml['nc']:
|
||||
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
|
||||
self.yaml['nc'] = nc # override yaml value
|
||||
if anchors:
|
||||
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
|
||||
self.yaml['anchors'] = round(anchors) # override yaml value
|
||||
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
|
||||
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
|
||||
self.inplace = self.yaml.get('inplace', True)
|
||||
|
||||
# Build strides, anchors
|
||||
m = self.model[-1] # Detect()
|
||||
if isinstance(m, Detect) or isinstance(m, CLLADetect):
|
||||
s = 256 # 2x min stride
|
||||
m.inplace = self.inplace
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
check_anchor_order(m)
|
||||
self.stride = m.stride
|
||||
self._initialize_biases() # only run once
|
||||
|
||||
# Init weights, biases
|
||||
initialize_weights(self)
|
||||
self.info()
|
||||
LOGGER.info('')
|
||||
|
||||
def forward(self, x, augment=False, profile=False, visualize=False):
|
||||
if augment:
|
||||
return self._forward_augment(x) # augmented inference, None
|
||||
return self._forward_once(x, profile, visualize) # single-scale inference, train
|
||||
|
||||
def _forward_augment(self, x):
|
||||
img_size = x.shape[-2:] # height, width
|
||||
s = [1, 1, 0.83, 0.83, 0.67, 0.67] # scales
|
||||
f = [None, 3, None, 3, None, 3] # flips (2-ud, 3-lr)
|
||||
y = [] # outputs
|
||||
for si, fi in zip(s, f):
|
||||
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
|
||||
yi = self._forward_once(xi)[0] # forward
|
||||
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
|
||||
yi = self._descale_pred(yi, fi, si, img_size)
|
||||
y.append(yi)
|
||||
y = self._clip_augmented(y) # clip augmented tails
|
||||
return torch.cat(y, 1), None # augmented inference, train
|
||||
|
||||
def _forward_once(self, x, profile=False, visualize=False):
|
||||
y, dt = [], [] # outputs
|
||||
for m in self.model:
|
||||
if m.f != -1: # if not from previous layer
|
||||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
|
||||
if profile:
|
||||
self._profile_one_layer(m, x, dt)
|
||||
x = m(x) # run
|
||||
y.append(x if m.i in self.save else None) # save output
|
||||
if visualize and m.type == 'models.common.C3STR':
|
||||
print(visualize)
|
||||
feature_visualization(x, m.type, m.i, save_dir=visualize)
|
||||
return x
|
||||
|
||||
def _descale_pred(self, p, flips, scale, img_size):
|
||||
# de-scale predictions following augmented inference (inverse operation)
|
||||
if self.inplace:
|
||||
p[..., :4] /= scale # de-scale
|
||||
if flips == 2:
|
||||
p[..., 1] = img_size[0] - p[..., 1] # de-flip ud
|
||||
elif flips == 3:
|
||||
p[..., 0] = img_size[1] - p[..., 0] # de-flip lr
|
||||
else:
|
||||
x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale
|
||||
if flips == 2:
|
||||
y = img_size[0] - y # de-flip ud
|
||||
elif flips == 3:
|
||||
x = img_size[1] - x # de-flip lr
|
||||
p = torch.cat((x, y, wh, p[..., 4:]), -1)
|
||||
return p
|
||||
|
||||
def _clip_augmented(self, y):
|
||||
# Clip YOLOv5 augmented inference tails
|
||||
nl = self.model[-1].nl # number of detection layers (P3-P5)
|
||||
g = sum(4 ** x for x in range(nl)) # grid points
|
||||
e = 1 # exclude layer count
|
||||
i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indices
|
||||
y[0] = y[0][:, :-i] # large
|
||||
i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices
|
||||
y[-1] = y[-1][:, i:] # small
|
||||
return y
|
||||
|
||||
def _profile_one_layer(self, m, x, dt):
|
||||
c = isinstance(m, Detect) # is final layer, copy input as inplace fix
|
||||
o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
|
||||
t = time_sync()
|
||||
for _ in range(10):
|
||||
m(x.copy() if c else x)
|
||||
dt.append((time_sync() - t) * 100)
|
||||
if m == self.model[0]:
|
||||
LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} {'module'}")
|
||||
LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}')
|
||||
if c:
|
||||
LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total")
|
||||
|
||||
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||||
# https://arxiv.org/abs/1708.02002 section 3.3
|
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
|
||||
m = self.model[-1] # Detect() module
|
||||
|
||||
if isinstance(m, Detect):
|
||||
for mi, s in zip(m.m, m.stride): # from
|
||||
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
else:
|
||||
for mi, s in zip(m.m, m.stride[1:]): # from
|
||||
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
b = m.det.det.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
b.data[:, 4] += math.log(8 / (640 / m.stride[0]) ** 2) # obj (8 objects per 640 image)
|
||||
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
m.det.det.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
|
||||
def _print_biases(self):
|
||||
m = self.model[-1] # Detect() module
|
||||
if getattr(m.m, 'bias', False):
|
||||
for mi in m.m: # from
|
||||
b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
|
||||
LOGGER.info(
|
||||
('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
|
||||
else:
|
||||
for mi in m.m: # from
|
||||
b1 = mi.cls.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
|
||||
b2 = mi.bbox.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
|
||||
LOGGER.info(
|
||||
('%6g Conv2d.bias and %6g Conv2d.bias:' + '%10.3g' * 6) % (mi.bbox.weight.shape[1], mi.cls.weight.shape[1], *b2[:].mean(1).tolist(), b1[:].mean()))
|
||||
|
||||
|
||||
# def _print_weights(self):
|
||||
# for m in self.model.modules():
|
||||
# if type(m) is Bottleneck:
|
||||
# LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
|
||||
|
||||
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
|
||||
LOGGER.info('Fusing layers... ')
|
||||
for m in self.model.modules():
|
||||
if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
|
||||
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
|
||||
delattr(m, 'bn') # remove batchnorm
|
||||
m.forward = m.forward_fuse # update forward
|
||||
self.info()
|
||||
return self
|
||||
|
||||
def autoshape(self): # add AutoShape module
|
||||
LOGGER.info('Adding AutoShape... ')
|
||||
m = AutoShape(self) # wrap model
|
||||
copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=()) # copy attributes
|
||||
return m
|
||||
|
||||
def info(self, verbose=False, img_size=640): # print model information
|
||||
model_info(self, verbose, img_size)
|
||||
|
||||
def _apply(self, fn):
|
||||
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
|
||||
self = super()._apply(fn)
|
||||
m = self.model[-1] # Detect()
|
||||
if isinstance(m, Detect):
|
||||
m.stride = fn(m.stride)
|
||||
m.grid = list(map(fn, m.grid))
|
||||
if isinstance(m.anchor_grid, list):
|
||||
m.anchor_grid = list(map(fn, m.anchor_grid))
|
||||
return self
|
||||
|
||||
|
||||
def parse_model(d, ch): # model_dict, input_channels(3)
|
||||
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
|
||||
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
|
||||
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
|
||||
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
|
||||
|
||||
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
|
||||
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
|
||||
m = eval(m) if isinstance(m, str) else m # eval strings
|
||||
for j, a in enumerate(args):
|
||||
try:
|
||||
args[j] = eval(a) if isinstance(a, str) else a # eval strings
|
||||
except NameError:
|
||||
pass
|
||||
|
||||
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
|
||||
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
|
||||
BottleneckCSP, C3, C3TR, C3STR, C3SPP, C3Ghost, ASPP, CBAM, nn.ConvTranspose2d]:
|
||||
c1, c2 = ch[f], args[0]
|
||||
if c2 != no: # if not output
|
||||
c2 = make_divisible(c2 * gw, 8)
|
||||
|
||||
args = [c1, c2, *args[1:]]
|
||||
if m in [BottleneckCSP, C3, C3TR, C3STR, C3Ghost]:
|
||||
args.insert(2, n) # number of repeats
|
||||
n = 1
|
||||
elif m is nn.BatchNorm2d:
|
||||
args = [ch[f]]
|
||||
elif m is Concat:
|
||||
c2 = sum(ch[x] for x in f)
|
||||
elif m is Detect:
|
||||
args.append([ch[x] for x in f])
|
||||
if isinstance(args[1], int): # number of anchors
|
||||
args[1] = [list(range(args[1] * 2))] * len(f)
|
||||
elif m is CLLADetect:
|
||||
args.append([ch[x] for x in f])
|
||||
if isinstance(args[1], int): # number of anchors
|
||||
args[1] = [list(range(args[1] * 2))] * (len(f) - 1)
|
||||
elif m is Contract:
|
||||
c2 = ch[f] * args[0] ** 2
|
||||
elif m is Expand:
|
||||
c2 = ch[f] // args[0] ** 2
|
||||
else:
|
||||
c2 = ch[f]
|
||||
|
||||
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
|
||||
t = str(m)[8:-2].replace('__main__.', '') # module type
|
||||
np = sum(x.numel() for x in m_.parameters()) # number params
|
||||
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
|
||||
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # print
|
||||
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
|
||||
layers.append(m_)
|
||||
if i == 0:
|
||||
ch = []
|
||||
ch.append(c2)
|
||||
return nn.Sequential(*layers), sorted(save)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--profile', action='store_true', help='profile model speed')
|
||||
opt = parser.parse_args()
|
||||
opt.cfg = check_yaml(opt.cfg) # check YAML
|
||||
print_args(FILE.stem, opt)
|
||||
device = select_device(opt.device)
|
||||
|
||||
# Create model
|
||||
model = Model(opt.cfg).to(device)
|
||||
model.train()
|
||||
|
||||
# Profile
|
||||
if opt.profile:
|
||||
img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
|
||||
y = model(img, profile=True)
|
||||
|
||||
# Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
|
||||
# from torch.utils.tensorboard import SummaryWriter
|
||||
# tb_writer = SummaryWriter('.')
|
||||
# LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
|
||||
# tb_writer.add_graph(torch.jit.trace(model, img, strict=False), []) # add model graph
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3
|
||||
# - [10,13, 16,30, 33,23] # P3/8
|
||||
# - [30,61, 62,45, 59,119] # P4/16
|
||||
# - [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 1, C3STR, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[2, 17, 20, 23], 1, CLLADetect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,57 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 4
|
||||
# - [10,13, 16,30, 33,23] # P3/8
|
||||
# - [30,61, 62,45, 59,119] # P4/16
|
||||
# - [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 128, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 2 ], 1, Concat, [ 1 ] ], # cat backbone P2
|
||||
[ -1, 2, C3STR, [ 128, False ] ], # 21 (P2/4-xsmall)
|
||||
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ],
|
||||
[ [ -1, 18, 4], 1, Concat, [ 1 ] ], # cat head P3
|
||||
[ -1, 2, C3STR, [ 256, False ] ], # 24 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14, 6], 1, Concat, [1]], # cat head P4
|
||||
[-1, 2, C3STR, [512, False]], # 27 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 2, C3STR, [1024, False]], # 30 (P5/32-large)
|
||||
|
||||
[[21, 24, 27, 30], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,65 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 4
|
||||
# - [10,13, 16,30, 33,23] # P3/8
|
||||
# - [30,61, 62,45, 59,119] # P4/16
|
||||
# - [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3TR, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 128, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 2 ], 1, Concat, [ 1 ] ], # cat backbone P2
|
||||
[-1, 1, SPP, [128, [5, 9, 13]]],
|
||||
[ -1, 3, C3, [ 128, False ] ], # (P2/4-xsmall)
|
||||
[-1, 1, CBAM, [128]], # 23
|
||||
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ],
|
||||
[ [ -1, 18, 4], 1, Concat, [ 1 ] ], # cat head P3
|
||||
[-1, 1, SPP, [256, [5, 9, 13]]],
|
||||
[ -1, 3, C3, [ 256, False ] ], # (P3/8-small)
|
||||
[-1, 1, CBAM, [256]], # 28
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14, 6], 1, Concat, [1]], # cat head P4
|
||||
[-1, 1, SPP, [512, [3, 7, 11]]],
|
||||
[-1, 3, C3, [512, False]], # (P4/16-medium)
|
||||
[-1, 1, CBAM, [512]], # 33
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 1, SPP, [1024, [3, 5, 7]]],
|
||||
[-1, 3, C3TR, [1024, False]], # (P5/32-large)
|
||||
[-1, 1, CBAM, [1024]], # 38
|
||||
|
||||
[[23, 28, 33, 38], 1, Detect, [nc,anchors]], # Detect(P2, P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.67 # model depth multiple
|
||||
width_multiple: 0.75 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.25 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.33 # model depth multiple
|
||||
width_multiple: 1.25 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,37 @@
|
|||
# pip install -r requirements.txt
|
||||
|
||||
# Base ----------------------------------------
|
||||
#matplotlib>=3.2.2
|
||||
#numpy>=1.18.5
|
||||
#opencv-python>=4.1.2
|
||||
#Pillow>=7.1.2
|
||||
#PyYAML>=5.3.1
|
||||
#requests>=2.23.0
|
||||
#scipy>=1.4.1
|
||||
#torch>=1.7.0
|
||||
#torchvision>=0.8.1
|
||||
#tqdm>=4.41.0
|
||||
|
||||
# Logging -------------------------------------
|
||||
#wandtensorboard>=2.4.1
|
||||
#wandb
|
||||
|
||||
# Plotting ------------------------------------
|
||||
#pandas>=1.1.4
|
||||
#seaborn>=0.11.0
|
||||
|
||||
# Export --------------------------------------
|
||||
# coremltools>=4.1 # CoreML export
|
||||
# onnx>=1.9.0 # ONNX export
|
||||
# onnx-simplifier>=0.3.6 # ONNX simplifier
|
||||
# scikit-learn==0.19.2 # CoreML quantization
|
||||
# tensorflow>=2.4.1 # TFLite export
|
||||
# tensorflowjs>=3.9.0 # TF.js export
|
||||
|
||||
# Extras --------------------------------------
|
||||
#albumentations>=1.0.3
|
||||
# Cython # for pycocotools https://github.com/cocodataset/cocoapi/issues/172
|
||||
# pycocotools>=2.0 # COCO mAP
|
||||
# roboflow
|
||||
#thop # FLOPs computation
|
||||
#ensemble_boxes
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 100 KiB |
|
|
@ -0,0 +1,51 @@
|
|||
# Project-wide configuration file, can be used for package metadata and other toll configurations
|
||||
# Example usage: global configuration for PEP8 (via flake8) setting or default pytest arguments
|
||||
|
||||
[metadata]
|
||||
license_file = LICENSE
|
||||
description-file = README.md
|
||||
|
||||
|
||||
[tool:pytest]
|
||||
norecursedirs =
|
||||
.git
|
||||
dist
|
||||
build
|
||||
addopts =
|
||||
--doctest-modules
|
||||
--durations=25
|
||||
--color=yes
|
||||
|
||||
|
||||
[flake8]
|
||||
max-line-length = 120
|
||||
exclude = .tox,*.egg,build,temp
|
||||
select = E,W,F
|
||||
doctests = True
|
||||
verbose = 2
|
||||
# https://pep8.readthedocs.io/en/latest/intro.html#error-codes
|
||||
format = pylint
|
||||
# see: https://www.flake8rules.com/
|
||||
ignore =
|
||||
E731 # Do not assign a lambda expression, use a def
|
||||
F405
|
||||
E402
|
||||
F841
|
||||
E741
|
||||
F821
|
||||
E722
|
||||
F401
|
||||
W504
|
||||
E127
|
||||
W504
|
||||
E231
|
||||
E501
|
||||
F403
|
||||
E302
|
||||
F541
|
||||
|
||||
|
||||
[isort]
|
||||
# https://pycqa.github.io/isort/docs/configuration/options.html
|
||||
line_length = 120
|
||||
multi_line_output = 0
|
||||
|
|
@ -0,0 +1,630 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Train a YOLOv5 model on a custom dataset
|
||||
|
||||
Usage:
|
||||
$ python path/to/train.py --data coco128.yaml --weights yolov5s.pt --img 640
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
import sys
|
||||
import time
|
||||
from copy import deepcopy
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.distributed as dist
|
||||
import torch.nn as nn
|
||||
import yaml
|
||||
from torch.cuda import amp
|
||||
from torch.nn.parallel import DistributedDataParallel as DDP
|
||||
from torch.optim import SGD, Adam, lr_scheduler
|
||||
from tqdm import tqdm
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[0] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
|
||||
|
||||
import val # for end-of-epoch mAP
|
||||
from models.experimental import attempt_load
|
||||
from models.yolo import Model
|
||||
from utils.autoanchor import check_anchors
|
||||
from utils.autobatch import check_train_batch_size
|
||||
from utils.callbacks import Callbacks
|
||||
from utils.datasets import create_dataloader
|
||||
from utils.downloads import attempt_download
|
||||
from utils.general import (LOGGER, check_dataset, check_file, check_git_status, check_img_size, check_requirements,
|
||||
check_suffix, check_yaml, colorstr, get_latest_run, increment_path, init_seeds,
|
||||
labels_to_class_weights, labels_to_image_weights, methods, one_cycle, print_args,
|
||||
print_mutation, strip_optimizer)
|
||||
from utils.loggers import Loggers
|
||||
from utils.loggers.wandb.wandb_utils import check_wandb_resume
|
||||
from utils.loss import ComputeLoss
|
||||
from utils.metrics import fitness
|
||||
from utils.plots import plot_evolve, plot_labels
|
||||
from utils.torch_utils import (EarlyStopping, ModelEMA, de_parallel, intersect_dicts, select_device,
|
||||
torch_distributed_zero_first)
|
||||
|
||||
LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html
|
||||
RANK = int(os.getenv('RANK', -1))
|
||||
WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))
|
||||
|
||||
|
||||
def train(hyp, # path/to/hyp.yaml or hyp dictionary
|
||||
opt,
|
||||
device,
|
||||
callbacks
|
||||
):
|
||||
save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze, = \
|
||||
Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \
|
||||
opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze
|
||||
|
||||
# Directories
|
||||
w = save_dir / 'weights' # weights dir
|
||||
(w.parent if evolve else w).mkdir(parents=True, exist_ok=True) # make dir
|
||||
last, best = w / 'last.pt', w / 'best.pt'
|
||||
|
||||
# Hyperparameters
|
||||
if isinstance(hyp, str):
|
||||
with open(hyp, errors='ignore') as f:
|
||||
hyp = yaml.safe_load(f) # load hyps dict
|
||||
LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
|
||||
|
||||
# Save run settings
|
||||
with open(save_dir / 'hyp.yaml', 'w') as f:
|
||||
yaml.safe_dump(hyp, f, sort_keys=False)
|
||||
with open(save_dir / 'opt.yaml', 'w') as f:
|
||||
yaml.safe_dump(vars(opt), f, sort_keys=False)
|
||||
data_dict = None
|
||||
|
||||
# Loggers
|
||||
if RANK in [-1, 0]:
|
||||
loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance
|
||||
if loggers.wandb:
|
||||
data_dict = loggers.wandb.data_dict
|
||||
if resume:
|
||||
weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp
|
||||
|
||||
# Register actions
|
||||
for k in methods(loggers):
|
||||
callbacks.register_action(k, callback=getattr(loggers, k))
|
||||
|
||||
# Config
|
||||
plots = not evolve # create plots
|
||||
cuda = device.type != 'cpu'
|
||||
init_seeds(1 + RANK)
|
||||
with torch_distributed_zero_first(LOCAL_RANK):
|
||||
data_dict = data_dict or check_dataset(data) # check if None
|
||||
train_path, val_path = data_dict['train'], data_dict['val']
|
||||
nc = 1 if single_cls else int(data_dict['nc']) # number of classes
|
||||
names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names
|
||||
assert len(names) == nc, f'{len(names)} names found for nc={nc} dataset in {data}' # check
|
||||
is_coco = isinstance(val_path, str) and val_path.endswith('coco/val2017.txt') # COCO dataset
|
||||
|
||||
# Model
|
||||
check_suffix(weights, '.pt') # check weights
|
||||
pretrained = weights.endswith('.pt')
|
||||
if pretrained:
|
||||
with torch_distributed_zero_first(LOCAL_RANK):
|
||||
weights = attempt_download(weights) # download if not found locally
|
||||
ckpt = torch.load(weights, map_location=device) # load checkpoint
|
||||
model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
|
||||
exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else [] # exclude keys
|
||||
csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
|
||||
csd = intersect_dicts(csd, model.state_dict(), exclude=exclude) # intersect
|
||||
model.load_state_dict(csd, strict=False) # load
|
||||
LOGGER.info(f'Transferred {len(csd)}/{len(model.state_dict())} items from {weights}') # report
|
||||
else:
|
||||
model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
|
||||
|
||||
# Freeze
|
||||
freeze = [f'model.{x}.' for x in range(freeze)] # layers to freeze
|
||||
for k, v in model.named_parameters():
|
||||
v.requires_grad = True # train all layers
|
||||
if any(x in k for x in freeze):
|
||||
LOGGER.info(f'freezing {k}')
|
||||
v.requires_grad = False
|
||||
|
||||
# Image size
|
||||
gs = max(int(model.stride.max()), 32) # grid size (max stride)
|
||||
imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2) # verify imgsz is gs-multiple
|
||||
|
||||
# Batch size
|
||||
if RANK == -1 and batch_size == -1: # single-GPU only, estimate best batch size
|
||||
batch_size = check_train_batch_size(model, imgsz)
|
||||
|
||||
# Optimizer
|
||||
nbs = 64 # nominal batch size
|
||||
accumulate = max(round(nbs / batch_size), 1) # accumulate loss before optimizing
|
||||
hyp['weight_decay'] *= batch_size * accumulate / nbs # scale weight_decay
|
||||
LOGGER.info(f"Scaled weight_decay = {hyp['weight_decay']}")
|
||||
|
||||
g0, g1, g2 = [], [], [] # optimizer parameter groups
|
||||
for v in model.modules():
|
||||
if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter): # bias
|
||||
g2.append(v.bias)
|
||||
if isinstance(v, nn.BatchNorm2d): # weight (no decay)
|
||||
g0.append(v.weight)
|
||||
elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter): # weight (with decay)
|
||||
g1.append(v.weight)
|
||||
|
||||
if opt.adam:
|
||||
optimizer = Adam(g0, lr=3e-4, betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
|
||||
else:
|
||||
optimizer = SGD(g0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
|
||||
|
||||
optimizer.add_param_group({'params': g1, 'weight_decay': hyp['weight_decay']}) # add g1 with weight_decay
|
||||
optimizer.add_param_group({'params': g2}) # add g2 (biases)
|
||||
LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups "
|
||||
f"{len(g0)} weight, {len(g1)} weight (no decay), {len(g2)} bias")
|
||||
del g0, g1, g2
|
||||
|
||||
# Scheduler
|
||||
if opt.linear_lr:
|
||||
lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear
|
||||
else:
|
||||
lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf']
|
||||
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) # plot_lr_scheduler(optimizer, scheduler, epochs)
|
||||
|
||||
# EMA
|
||||
ema = ModelEMA(model) if RANK in [-1, 0] else None
|
||||
|
||||
# Resume
|
||||
start_epoch, best_fitness = 0, 0.0
|
||||
if pretrained:
|
||||
# Optimizer
|
||||
if ckpt['optimizer'] is not None:
|
||||
optimizer.load_state_dict(ckpt['optimizer'])
|
||||
best_fitness = ckpt['best_fitness']
|
||||
|
||||
# EMA
|
||||
if ema and ckpt.get('ema'):
|
||||
ema.ema.load_state_dict(ckpt['ema'].float().state_dict())
|
||||
ema.updates = ckpt['updates']
|
||||
|
||||
# Epochs
|
||||
start_epoch = ckpt['epoch'] + 1
|
||||
if resume:
|
||||
assert start_epoch > 0, f'{weights} training to {epochs} epochs is finished, nothing to resume.'
|
||||
if epochs < start_epoch:
|
||||
LOGGER.info(f"{weights} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {epochs} more epochs.")
|
||||
epochs += ckpt['epoch'] # finetune additional epochs
|
||||
|
||||
del ckpt, csd
|
||||
|
||||
# DP mode
|
||||
if cuda and RANK == -1 and torch.cuda.device_count() > 1:
|
||||
logging.warning('DP not recommended, instead use torch.distributed.run for best DDP Multi-GPU results.\n'
|
||||
'See Multi-GPU Tutorial at https://github.com/ultralytics/yolov5/issues/475 to get started.')
|
||||
model = torch.nn.DataParallel(model)
|
||||
|
||||
# SyncBatchNorm
|
||||
if opt.sync_bn and cuda and RANK != -1:
|
||||
model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
|
||||
LOGGER.info('Using SyncBatchNorm()')
|
||||
|
||||
# Trainloader
|
||||
train_loader, dataset = create_dataloader(train_path, imgsz, batch_size // WORLD_SIZE, gs, single_cls,
|
||||
hyp=hyp, augment=True, cache=opt.cache, rect=opt.rect, rank=LOCAL_RANK,
|
||||
workers=workers, image_weights=opt.image_weights, quad=opt.quad,
|
||||
prefix=colorstr('train: '))
|
||||
mlc = int(np.concatenate(dataset.labels, 0)[:, 0].max()) # max label class
|
||||
nb = len(train_loader) # number of batches
|
||||
assert mlc < nc, f'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}'
|
||||
|
||||
# Process 0
|
||||
if RANK in [-1, 0]:
|
||||
val_loader = create_dataloader(val_path, imgsz, batch_size // WORLD_SIZE * 2, gs, single_cls,
|
||||
hyp=hyp, cache=None if noval else opt.cache, rect=True, rank=-1,
|
||||
workers=workers, pad=0.5,
|
||||
prefix=colorstr('val: '))[0]
|
||||
|
||||
if not resume:
|
||||
labels = np.concatenate(dataset.labels, 0)
|
||||
# c = torch.tensor(labels[:, 0]) # classes
|
||||
# cf = torch.bincount(c.long(), minlength=nc) + 1. # frequency
|
||||
# model._initialize_biases(cf.to(device))
|
||||
if plots:
|
||||
plot_labels(labels, names, save_dir)
|
||||
|
||||
# Anchors
|
||||
if not opt.noautoanchor:
|
||||
check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
|
||||
model.half().float() # pre-reduce anchor precision
|
||||
|
||||
callbacks.run('on_pretrain_routine_end')
|
||||
|
||||
# DDP mode
|
||||
if cuda and RANK != -1:
|
||||
# model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK)
|
||||
model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK,find_unused_parameters=any(isinstance(layer, nn.MultiheadAttention) for layer in model.modules()))
|
||||
|
||||
|
||||
# Model parameters
|
||||
nl = de_parallel(model).model[-1].nl # number of detection layers (to scale hyps)
|
||||
hyp['box'] *= 3 / nl # scale to layers
|
||||
hyp['cls'] *= nc / 80 * 3 / nl # scale to classes and layers
|
||||
hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers
|
||||
hyp['label_smoothing'] = opt.label_smoothing
|
||||
model.nc = nc # attach number of classes to model
|
||||
model.hyp = hyp # attach hyperparameters to model
|
||||
model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights
|
||||
model.names = names
|
||||
|
||||
# Start training
|
||||
t0 = time.time()
|
||||
nw = max(round(hyp['warmup_epochs'] * nb), 1000) # number of warmup iterations, max(3 epochs, 1k iterations)
|
||||
# nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training
|
||||
last_opt_step = -1
|
||||
maps = np.zeros(nc) # mAP per class
|
||||
results = (0, 0, 0, 0, 0, 0, 0) # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
|
||||
scheduler.last_epoch = start_epoch - 1 # do not move
|
||||
scaler = amp.GradScaler(enabled=cuda)
|
||||
stopper = EarlyStopping(patience=opt.patience)
|
||||
compute_loss = ComputeLoss(model) # init loss class
|
||||
LOGGER.info(f'Image sizes {imgsz} train, {imgsz} val\n'
|
||||
f'Using {train_loader.num_workers} dataloader workers\n'
|
||||
f"Logging results to {colorstr('bold', save_dir)}\n"
|
||||
f'Starting training for {epochs} epochs...')
|
||||
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
|
||||
model.train()
|
||||
|
||||
# Update image weights (optional, single-GPU only)
|
||||
if opt.image_weights:
|
||||
cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc # class weights
|
||||
iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw) # image weights
|
||||
dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n) # rand weighted idx
|
||||
|
||||
# Update mosaic border (optional)
|
||||
# b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
|
||||
# dataset.mosaic_border = [b - imgsz, -b] # height, width borders
|
||||
|
||||
mloss = torch.zeros(3, device=device) # mean losses
|
||||
if RANK != -1:
|
||||
train_loader.sampler.set_epoch(epoch)
|
||||
pbar = enumerate(train_loader)
|
||||
LOGGER.info(('\n' + '%10s' * 7) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'labels', 'img_size'))
|
||||
if RANK in [-1, 0]:
|
||||
pbar = tqdm(pbar, total=nb) # progress bar
|
||||
optimizer.zero_grad()
|
||||
for i, (imgs, targets, paths, _) in pbar: # batch -------------------------------------------------------------
|
||||
ni = i + nb * epoch # number integrated batches (since train start)
|
||||
imgs = imgs.to(device, non_blocking=True).float() / 255 # uint8 to float32, 0-255 to 0.0-1.0
|
||||
|
||||
# Warmup
|
||||
if ni <= nw:
|
||||
xi = [0, nw] # x interp
|
||||
# compute_loss.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou)
|
||||
accumulate = max(1, np.interp(ni, xi, [1, nbs / batch_size]).round())
|
||||
for j, x in enumerate(optimizer.param_groups):
|
||||
# bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
|
||||
x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
|
||||
if 'momentum' in x:
|
||||
x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
|
||||
|
||||
# Multi-scale
|
||||
if opt.multi_scale:
|
||||
sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs # size
|
||||
sf = sz / max(imgs.shape[2:]) # scale factor
|
||||
if sf != 1:
|
||||
ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple)
|
||||
imgs = nn.functional.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
|
||||
|
||||
# Forward
|
||||
with amp.autocast(enabled=cuda):
|
||||
pred = model(imgs) # forward
|
||||
loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size
|
||||
if RANK != -1:
|
||||
loss *= WORLD_SIZE # gradient averaged between devices in DDP mode
|
||||
if opt.quad:
|
||||
loss *= 4.
|
||||
|
||||
# Backward
|
||||
scaler.scale(loss).backward()
|
||||
|
||||
# Optimize
|
||||
if ni - last_opt_step >= accumulate:
|
||||
scaler.step(optimizer) # optimizer.step
|
||||
scaler.update()
|
||||
optimizer.zero_grad()
|
||||
if ema:
|
||||
ema.update(model)
|
||||
last_opt_step = ni
|
||||
|
||||
# Log
|
||||
if RANK in [-1, 0]:
|
||||
mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
|
||||
mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G' # (GB)
|
||||
pbar.set_description(('%10s' * 2 + '%10.4g' * 5) % (
|
||||
f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]))
|
||||
callbacks.run('on_train_batch_end', ni, model, imgs, targets, paths, plots, opt.sync_bn)
|
||||
# end batch ------------------------------------------------------------------------------------------------
|
||||
|
||||
# Scheduler
|
||||
lr = [x['lr'] for x in optimizer.param_groups] # for loggers
|
||||
scheduler.step()
|
||||
|
||||
if RANK in [-1, 0]:
|
||||
# mAP
|
||||
callbacks.run('on_train_epoch_end', epoch=epoch)
|
||||
ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'names', 'stride', 'class_weights'])
|
||||
final_epoch = (epoch + 1 == epochs) or stopper.possible_stop
|
||||
if not noval or final_epoch: # Calculate mAP
|
||||
results, maps, _ = val.run(data_dict,
|
||||
batch_size=batch_size // WORLD_SIZE * 2,
|
||||
imgsz=imgsz,
|
||||
model=ema.ema,
|
||||
single_cls=single_cls,
|
||||
dataloader=val_loader,
|
||||
save_dir=save_dir,
|
||||
plots=False,
|
||||
callbacks=callbacks,
|
||||
compute_loss=compute_loss)
|
||||
|
||||
# Update best mAP
|
||||
fi = fitness(np.array(results).reshape(1, -1)) # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
|
||||
if fi > best_fitness:
|
||||
best_fitness = fi
|
||||
log_vals = list(mloss) + list(results) + lr
|
||||
callbacks.run('on_fit_epoch_end', log_vals, epoch, best_fitness, fi)
|
||||
|
||||
# Save model
|
||||
if (not nosave) or (final_epoch and not evolve): # if save
|
||||
ckpt = {'epoch': epoch,
|
||||
'best_fitness': best_fitness,
|
||||
'model': deepcopy(de_parallel(model)).half(),
|
||||
'ema': deepcopy(ema.ema).half(),
|
||||
'updates': ema.updates,
|
||||
'optimizer': optimizer.state_dict(),
|
||||
'wandb_id': loggers.wandb.wandb_run.id if loggers.wandb else None,
|
||||
'date': datetime.now().isoformat()}
|
||||
|
||||
# Save last, best and delete
|
||||
torch.save(ckpt, last)
|
||||
if best_fitness == fi:
|
||||
torch.save(ckpt, best)
|
||||
if (epoch > 0) and (opt.save_period > 0) and (epoch % opt.save_period == 0):
|
||||
torch.save(ckpt, w / f'epoch{epoch}.pt')
|
||||
del ckpt
|
||||
callbacks.run('on_model_save', last, epoch, final_epoch, best_fitness, fi)
|
||||
|
||||
# Stop Single-GPU
|
||||
if RANK == -1 and stopper(epoch=epoch, fitness=fi):
|
||||
break
|
||||
|
||||
# Stop DDP TODO: known issues shttps://github.com/ultralytics/yolov5/pull/4576
|
||||
# stop = stopper(epoch=epoch, fitness=fi)
|
||||
# if RANK == 0:
|
||||
# dist.broadcast_object_list([stop], 0) # broadcast 'stop' to all ranks
|
||||
|
||||
# Stop DPP
|
||||
# with torch_distributed_zero_first(RANK):
|
||||
# if stop:
|
||||
# break # must break all DDP ranks
|
||||
|
||||
# end epoch ----------------------------------------------------------------------------------------------------
|
||||
# end training -----------------------------------------------------------------------------------------------------
|
||||
if RANK in [-1, 0]:
|
||||
LOGGER.info(f'\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.')
|
||||
for f in last, best:
|
||||
if f.exists():
|
||||
strip_optimizer(f) # strip optimizers
|
||||
if f is best:
|
||||
LOGGER.info(f'\nValidating {f}...')
|
||||
results, _, _ = val.run(data_dict,
|
||||
batch_size=batch_size // WORLD_SIZE * 2,
|
||||
imgsz=imgsz,
|
||||
model=attempt_load(f, device).half(),
|
||||
iou_thres=0.65 if is_coco else 0.60, # best pycocotools results at 0.65
|
||||
single_cls=single_cls,
|
||||
dataloader=val_loader,
|
||||
save_dir=save_dir,
|
||||
save_json=is_coco,
|
||||
verbose=True,
|
||||
plots=True,
|
||||
callbacks=callbacks,
|
||||
compute_loss=compute_loss) # val best model with plots
|
||||
if is_coco:
|
||||
callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi)
|
||||
|
||||
callbacks.run('on_train_end', last, best, plots, epoch, results)
|
||||
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")
|
||||
|
||||
torch.cuda.empty_cache()
|
||||
return results
|
||||
|
||||
|
||||
def parse_opt(known=False):
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path')
|
||||
parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
|
||||
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
|
||||
parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch.yaml', help='hyperparameters path')
|
||||
parser.add_argument('--epochs', type=int, default=300)
|
||||
parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs, -1 for autobatch')
|
||||
parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
|
||||
parser.add_argument('--rect', action='store_true', help='rectangular training')
|
||||
parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
|
||||
parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
|
||||
parser.add_argument('--noval', action='store_true', help='only validate final epoch')
|
||||
parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
|
||||
parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
|
||||
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
|
||||
parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"')
|
||||
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
|
||||
parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
|
||||
parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
|
||||
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
|
||||
parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
|
||||
parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name')
|
||||
parser.add_argument('--name', default='exp', help='save to project/name')
|
||||
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
|
||||
parser.add_argument('--quad', action='store_true', help='quad dataloader')
|
||||
parser.add_argument('--linear-lr', action='store_true', help='linear LR')
|
||||
parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
|
||||
parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
|
||||
parser.add_argument('--freeze', type=int, default=0, help='Number of layers to freeze. backbone=10, all=24')
|
||||
parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
|
||||
parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
|
||||
|
||||
# Weights & Biases arguments
|
||||
parser.add_argument('--entity', default=None, help='W&B: Entity')
|
||||
parser.add_argument('--upload_dataset', action='store_true', help='W&B: Upload dataset as artifact table')
|
||||
parser.add_argument('--bbox_interval', type=int, default=-1, help='W&B: Set bounding-box image logging interval')
|
||||
parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use')
|
||||
|
||||
opt = parser.parse_known_args()[0] if known else parser.parse_args()
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt, callbacks=Callbacks()):
|
||||
# Checks
|
||||
if RANK in [-1, 0]:
|
||||
print_args(FILE.stem, opt)
|
||||
check_git_status()
|
||||
check_requirements(exclude=['thop'])
|
||||
|
||||
# Resume
|
||||
if opt.resume and not check_wandb_resume(opt) and not opt.evolve: # resume an interrupted run
|
||||
ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path
|
||||
assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
|
||||
with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f:
|
||||
opt = argparse.Namespace(**yaml.safe_load(f)) # replace
|
||||
opt.cfg, opt.weights, opt.resume = '', ckpt, True # reinstate
|
||||
LOGGER.info(f'Resuming training from {ckpt}')
|
||||
else:
|
||||
opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \
|
||||
check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project) # checks
|
||||
assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
|
||||
if opt.evolve:
|
||||
opt.project = str(ROOT / 'runs/evolve')
|
||||
opt.exist_ok, opt.resume = opt.resume, False # pass resume to exist_ok and disable resume
|
||||
opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))
|
||||
|
||||
# DDP mode
|
||||
device = select_device(opt.device, batch_size=opt.batch_size)
|
||||
if LOCAL_RANK != -1:
|
||||
assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command'
|
||||
assert opt.batch_size % WORLD_SIZE == 0, '--batch-size must be multiple of CUDA device count'
|
||||
assert not opt.image_weights, '--image-weights argument is not compatible with DDP training'
|
||||
assert not opt.evolve, '--evolve argument is not compatible with DDP training'
|
||||
torch.cuda.set_device(LOCAL_RANK)
|
||||
device = torch.device('cuda', LOCAL_RANK)
|
||||
dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo")
|
||||
|
||||
# Train
|
||||
if not opt.evolve:
|
||||
train(opt.hyp, opt, device, callbacks)
|
||||
if WORLD_SIZE > 1 and RANK == 0:
|
||||
LOGGER.info('Destroying process group... ')
|
||||
dist.destroy_process_group()
|
||||
|
||||
# Evolve hyperparameters (optional)
|
||||
else:
|
||||
# Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
|
||||
meta = {'lr0': (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3)
|
||||
'lrf': (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
|
||||
'momentum': (0.3, 0.6, 0.98), # SGD momentum/Adam beta1
|
||||
'weight_decay': (1, 0.0, 0.001), # optimizer weight decay
|
||||
'warmup_epochs': (1, 0.0, 5.0), # warmup epochs (fractions ok)
|
||||
'warmup_momentum': (1, 0.0, 0.95), # warmup initial momentum
|
||||
'warmup_bias_lr': (1, 0.0, 0.2), # warmup initial bias lr
|
||||
'box': (1, 0.02, 0.2), # box loss gain
|
||||
'cls': (1, 0.2, 4.0), # cls loss gain
|
||||
'cls_pw': (1, 0.5, 2.0), # cls BCELoss positive_weight
|
||||
'obj': (1, 0.2, 4.0), # obj loss gain (scale with pixels)
|
||||
'obj_pw': (1, 0.5, 2.0), # obj BCELoss positive_weight
|
||||
'iou_t': (0, 0.1, 0.7), # IoU training threshold
|
||||
'anchor_t': (1, 2.0, 8.0), # anchor-multiple threshold
|
||||
'anchors': (2, 2.0, 10.0), # anchors per output grid (0 to ignore)
|
||||
'fl_gamma': (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5)
|
||||
'hsv_h': (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction)
|
||||
'hsv_s': (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction)
|
||||
'hsv_v': (1, 0.0, 0.9), # image HSV-Value augmentation (fraction)
|
||||
'degrees': (1, 0.0, 45.0), # image rotation (+/- deg)
|
||||
'translate': (1, 0.0, 0.9), # image translation (+/- fraction)
|
||||
'scale': (1, 0.0, 0.9), # image scale (+/- gain)
|
||||
'shear': (1, 0.0, 10.0), # image shear (+/- deg)
|
||||
'perspective': (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
|
||||
'flipud': (1, 0.0, 1.0), # image flip up-down (probability)
|
||||
'fliplr': (0, 0.0, 1.0), # image flip left-right (probability)
|
||||
'mosaic': (1, 0.0, 1.0), # image mixup (probability)
|
||||
'mixup': (1, 0.0, 1.0), # image mixup (probability)
|
||||
'copy_paste': (1, 0.0, 1.0)} # segment copy-paste (probability)
|
||||
|
||||
with open(opt.hyp, errors='ignore') as f:
|
||||
hyp = yaml.safe_load(f) # load hyps dict
|
||||
if 'anchors' not in hyp: # anchors commented in hyp.yaml
|
||||
hyp['anchors'] = 3
|
||||
opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir) # only val/save final epoch
|
||||
# ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices
|
||||
evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv'
|
||||
if opt.bucket:
|
||||
os.system(f'gsutil cp gs://{opt.bucket}/evolve.csv {save_dir}') # download evolve.csv if exists
|
||||
|
||||
for _ in range(opt.evolve): # generations to evolve
|
||||
if evolve_csv.exists(): # if evolve.csv exists: select best hyps and mutate
|
||||
# Select parent(s)
|
||||
parent = 'single' # parent selection method: 'single' or 'weighted'
|
||||
x = np.loadtxt(evolve_csv, ndmin=2, delimiter=',', skiprows=1)
|
||||
n = min(5, len(x)) # number of previous results to consider
|
||||
x = x[np.argsort(-fitness(x))][:n] # top n mutations
|
||||
w = fitness(x) - fitness(x).min() + 1E-6 # weights (sum > 0)
|
||||
if parent == 'single' or len(x) == 1:
|
||||
# x = x[random.randint(0, n - 1)] # random selection
|
||||
x = x[random.choices(range(n), weights=w)[0]] # weighted selection
|
||||
elif parent == 'weighted':
|
||||
x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination
|
||||
|
||||
# Mutate
|
||||
mp, s = 0.8, 0.2 # mutation probability, sigma
|
||||
npr = np.random
|
||||
npr.seed(int(time.time()))
|
||||
g = np.array([meta[k][0] for k in hyp.keys()]) # gains 0-1
|
||||
ng = len(meta)
|
||||
v = np.ones(ng)
|
||||
while all(v == 1): # mutate until a change occurs (prevent duplicates)
|
||||
v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
|
||||
for i, k in enumerate(hyp.keys()): # plt.hist(v.ravel(), 300)
|
||||
hyp[k] = float(x[i + 7] * v[i]) # mutate
|
||||
|
||||
# Constrain to limits
|
||||
for k, v in meta.items():
|
||||
hyp[k] = max(hyp[k], v[1]) # lower limit
|
||||
hyp[k] = min(hyp[k], v[2]) # upper limit
|
||||
hyp[k] = round(hyp[k], 5) # significant digits
|
||||
|
||||
# Train mutation
|
||||
results = train(hyp.copy(), opt, device, callbacks)
|
||||
|
||||
# Write mutation results
|
||||
print_mutation(results, hyp.copy(), save_dir, opt.bucket)
|
||||
|
||||
# Plot results
|
||||
plot_evolve(evolve_csv)
|
||||
LOGGER.info(f'Hyperparameter evolution finished\n'
|
||||
f"Results saved to {colorstr('bold', save_dir)}\n"
|
||||
f'Use best hyperparameters example: $ python train.py --hyp {evolve_yaml}')
|
||||
|
||||
|
||||
def run(**kwargs):
|
||||
# Usage: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
|
||||
opt = parse_opt(True)
|
||||
for k, v in kwargs.items():
|
||||
setattr(opt, k, v)
|
||||
main(opt)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1 @@
|
|||
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,101 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Activation functions
|
||||
"""
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
|
||||
# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
|
||||
class SiLU(nn.Module): # export-friendly version of nn.SiLU()
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
return x * torch.sigmoid(x)
|
||||
|
||||
|
||||
class Hardswish(nn.Module): # export-friendly version of nn.Hardswish()
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
# return x * F.hardsigmoid(x) # for torchscript and CoreML
|
||||
return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0 # for torchscript, CoreML and ONNX
|
||||
|
||||
|
||||
# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
|
||||
class Mish(nn.Module):
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
return x * F.softplus(x).tanh()
|
||||
|
||||
|
||||
class MemoryEfficientMish(nn.Module):
|
||||
class F(torch.autograd.Function):
|
||||
@staticmethod
|
||||
def forward(ctx, x):
|
||||
ctx.save_for_backward(x)
|
||||
return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x)))
|
||||
|
||||
@staticmethod
|
||||
def backward(ctx, grad_output):
|
||||
x = ctx.saved_tensors[0]
|
||||
sx = torch.sigmoid(x)
|
||||
fx = F.softplus(x).tanh()
|
||||
return grad_output * (fx + x * sx * (1 - fx * fx))
|
||||
|
||||
def forward(self, x):
|
||||
return self.F.apply(x)
|
||||
|
||||
|
||||
# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
|
||||
class FReLU(nn.Module):
|
||||
def __init__(self, c1, k=3): # ch_in, kernel
|
||||
super().__init__()
|
||||
self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
|
||||
self.bn = nn.BatchNorm2d(c1)
|
||||
|
||||
def forward(self, x):
|
||||
return torch.max(x, self.bn(self.conv(x)))
|
||||
|
||||
|
||||
# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------
|
||||
class AconC(nn.Module):
|
||||
r""" ACON activation (activate or not).
|
||||
AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
|
||||
according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
|
||||
"""
|
||||
|
||||
def __init__(self, c1):
|
||||
super().__init__()
|
||||
self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
|
||||
self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
|
||||
self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))
|
||||
|
||||
def forward(self, x):
|
||||
dpx = (self.p1 - self.p2) * x
|
||||
return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x
|
||||
|
||||
|
||||
class MetaAconC(nn.Module):
|
||||
r""" ACON activation (activate or not).
|
||||
MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
|
||||
according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
|
||||
"""
|
||||
|
||||
def __init__(self, c1, k=1, s=1, r=16): # ch_in, kernel, stride, r
|
||||
super().__init__()
|
||||
c2 = max(r, c1 // r)
|
||||
self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
|
||||
self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
|
||||
self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
|
||||
self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)
|
||||
# self.bn1 = nn.BatchNorm2d(c2)
|
||||
# self.bn2 = nn.BatchNorm2d(c1)
|
||||
|
||||
def forward(self, x):
|
||||
y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
|
||||
# batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891
|
||||
# beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y))))) # bug/unstable
|
||||
beta = torch.sigmoid(self.fc2(self.fc1(y))) # bug patch BN layers removed
|
||||
dpx = (self.p1 - self.p2) * x
|
||||
return dpx * torch.sigmoid(beta * dpx) + self.p2 * x
|
||||
|
|
@ -0,0 +1,278 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Image augmentation functions
|
||||
"""
|
||||
|
||||
import logging
|
||||
import math
|
||||
import random
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
from utils.general import check_version, colorstr, resample_segments, segment2box
|
||||
from utils.metrics import bbox_ioa
|
||||
|
||||
|
||||
class Albumentations:
|
||||
# YOLOv5 Albumentations class (optional, only used if package is installed)
|
||||
def __init__(self):
|
||||
self.transform = None
|
||||
try:
|
||||
import albumentations as A
|
||||
check_version(A.__version__, '1.0.3', hard=True) # version requirement
|
||||
|
||||
self.transform = A.Compose([
|
||||
A.Blur(p=0.01),
|
||||
A.MedianBlur(p=0.3),
|
||||
A.ToGray(p=0.01),
|
||||
A.CLAHE(p=0.3),
|
||||
A.RandomBrightnessContrast(p=0.3),
|
||||
A.RandomGamma(p=0.0),
|
||||
A.ImageCompression(quality_lower=75, p=0.0)],
|
||||
bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
|
||||
|
||||
logging.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p))
|
||||
except ImportError: # package not installed, skip
|
||||
pass
|
||||
except Exception as e:
|
||||
logging.info(colorstr('albumentations: ') + f'{e}')
|
||||
|
||||
def __call__(self, im, labels, p=1.0):
|
||||
if self.transform and random.random() < p:
|
||||
new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed
|
||||
im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])])
|
||||
return im, labels
|
||||
|
||||
|
||||
def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5):
|
||||
# HSV color-space augmentation
|
||||
if hgain or sgain or vgain:
|
||||
r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains
|
||||
hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV))
|
||||
dtype = im.dtype # uint8
|
||||
|
||||
x = np.arange(0, 256, dtype=r.dtype)
|
||||
lut_hue = ((x * r[0]) % 180).astype(dtype)
|
||||
lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
|
||||
lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
|
||||
|
||||
im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
|
||||
cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed
|
||||
|
||||
|
||||
def hist_equalize(im, clahe=True, bgr=False):
|
||||
# Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255
|
||||
yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV)
|
||||
if clahe:
|
||||
c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
|
||||
yuv[:, :, 0] = c.apply(yuv[:, :, 0])
|
||||
else:
|
||||
yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram
|
||||
return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB
|
||||
|
||||
|
||||
def replicate(im, labels):
|
||||
# Replicate labels
|
||||
h, w = im.shape[:2]
|
||||
boxes = labels[:, 1:].astype(int)
|
||||
x1, y1, x2, y2 = boxes.T
|
||||
s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels)
|
||||
for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices
|
||||
x1b, y1b, x2b, y2b = boxes[i]
|
||||
bh, bw = y2b - y1b, x2b - x1b
|
||||
yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y
|
||||
x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
|
||||
im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax]
|
||||
labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
|
||||
|
||||
return im, labels
|
||||
|
||||
|
||||
def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
|
||||
# Resize and pad image while meeting stride-multiple constraints
|
||||
shape = im.shape[:2] # current shape [height, width]
|
||||
if isinstance(new_shape, int):
|
||||
new_shape = (new_shape, new_shape)
|
||||
|
||||
# Scale ratio (new / old)
|
||||
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
|
||||
if not scaleup: # only scale down, do not scale up (for better val mAP)
|
||||
r = min(r, 1.0)
|
||||
|
||||
# Compute padding
|
||||
ratio = r, r # width, height ratios
|
||||
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
|
||||
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
|
||||
if auto: # minimum rectangle
|
||||
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
|
||||
elif scaleFill: # stretch
|
||||
dw, dh = 0.0, 0.0
|
||||
new_unpad = (new_shape[1], new_shape[0])
|
||||
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
|
||||
|
||||
dw /= 2 # divide padding into 2 sides
|
||||
dh /= 2
|
||||
|
||||
if shape[::-1] != new_unpad: # resize
|
||||
im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
|
||||
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
|
||||
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
|
||||
im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
|
||||
return im, ratio, (dw, dh)
|
||||
|
||||
|
||||
def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0,
|
||||
border=(0, 0)):
|
||||
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
|
||||
# targets = [cls, xyxy]
|
||||
|
||||
height = im.shape[0] + border[0] * 2 # shape(h,w,c)
|
||||
width = im.shape[1] + border[1] * 2
|
||||
|
||||
# Center
|
||||
C = np.eye(3)
|
||||
C[0, 2] = -im.shape[1] / 2 # x translation (pixels)
|
||||
C[1, 2] = -im.shape[0] / 2 # y translation (pixels)
|
||||
|
||||
# Perspective
|
||||
P = np.eye(3)
|
||||
P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y)
|
||||
P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x)
|
||||
|
||||
# Rotation and Scale
|
||||
R = np.eye(3)
|
||||
a = random.uniform(-degrees, degrees)
|
||||
# a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations
|
||||
s = random.uniform(1 - scale, 1 + scale)
|
||||
# s = 2 ** random.uniform(-scale, scale)
|
||||
R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
|
||||
|
||||
# Shear
|
||||
S = np.eye(3)
|
||||
S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg)
|
||||
S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg)
|
||||
|
||||
# Translation
|
||||
T = np.eye(3)
|
||||
T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels)
|
||||
T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels)
|
||||
|
||||
# Combined rotation matrix
|
||||
M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT
|
||||
if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed
|
||||
if perspective:
|
||||
im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114))
|
||||
else: # affine
|
||||
im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
|
||||
|
||||
# Visualize
|
||||
# import matplotlib.pyplot as plt
|
||||
# ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
|
||||
# ax[0].imshow(im[:, :, ::-1]) # base
|
||||
# ax[1].imshow(im2[:, :, ::-1]) # warped
|
||||
|
||||
# Transform label coordinates
|
||||
n = len(targets)
|
||||
if n:
|
||||
use_segments = any(x.any() for x in segments)
|
||||
new = np.zeros((n, 4))
|
||||
if use_segments: # warp segments
|
||||
segments = resample_segments(segments) # upsample
|
||||
for i, segment in enumerate(segments):
|
||||
xy = np.ones((len(segment), 3))
|
||||
xy[:, :2] = segment
|
||||
xy = xy @ M.T # transform
|
||||
xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine
|
||||
|
||||
# clip
|
||||
new[i] = segment2box(xy, width, height)
|
||||
|
||||
else: # warp boxes
|
||||
xy = np.ones((n * 4, 3))
|
||||
xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1
|
||||
xy = xy @ M.T # transform
|
||||
xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine
|
||||
|
||||
# create new boxes
|
||||
x = xy[:, [0, 2, 4, 6]]
|
||||
y = xy[:, [1, 3, 5, 7]]
|
||||
new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
|
||||
|
||||
# clip
|
||||
new[:, [0, 2]] = new[:, [0, 2]].clip(0, width)
|
||||
new[:, [1, 3]] = new[:, [1, 3]].clip(0, height)
|
||||
|
||||
# filter candidates
|
||||
i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10)
|
||||
targets = targets[i]
|
||||
targets[:, 1:5] = new[i]
|
||||
|
||||
return im, targets
|
||||
|
||||
|
||||
def copy_paste(im, labels, segments, p=0.5):
|
||||
# Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)
|
||||
n = len(segments)
|
||||
if p and n:
|
||||
h, w, c = im.shape # height, width, channels
|
||||
im_new = np.zeros(im.shape, np.uint8)
|
||||
for j in random.sample(range(n), k=round(p * n)):
|
||||
l, s = labels[j], segments[j]
|
||||
box = w - l[3], l[2], w - l[1], l[4]
|
||||
ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area
|
||||
if (ioa < 0.30).all(): # allow 30% obscuration of existing labels
|
||||
labels = np.concatenate((labels, [[l[0], *box]]), 0)
|
||||
segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
|
||||
cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED)
|
||||
|
||||
result = cv2.bitwise_and(src1=im, src2=im_new)
|
||||
result = cv2.flip(result, 1) # augment segments (flip left-right)
|
||||
i = result > 0 # pixels to replace
|
||||
# i[:, :] = result.max(2).reshape(h, w, 1) # act over ch
|
||||
im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug
|
||||
|
||||
return im, labels, segments
|
||||
|
||||
|
||||
def cutout(im, labels, p=0.5):
|
||||
# Applies image cutout augmentation https://arxiv.org/abs/1708.04552
|
||||
if random.random() < p:
|
||||
h, w = im.shape[:2]
|
||||
scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction
|
||||
for s in scales:
|
||||
mask_h = random.randint(1, int(h * s)) # create random masks
|
||||
mask_w = random.randint(1, int(w * s))
|
||||
|
||||
# box
|
||||
xmin = max(0, random.randint(0, w) - mask_w // 2)
|
||||
ymin = max(0, random.randint(0, h) - mask_h // 2)
|
||||
xmax = min(w, xmin + mask_w)
|
||||
ymax = min(h, ymin + mask_h)
|
||||
|
||||
# apply random color mask
|
||||
im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
|
||||
|
||||
# return unobscured labels
|
||||
if len(labels) and s > 0.03:
|
||||
box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
|
||||
ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area
|
||||
labels = labels[ioa < 0.60] # remove >60% obscured labels
|
||||
|
||||
return labels
|
||||
|
||||
|
||||
def mixup(im, labels, im2, labels2):
|
||||
# Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf
|
||||
r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0
|
||||
im = (im * r + im2 * (1 - r)).astype(np.uint8)
|
||||
labels = np.concatenate((labels, labels2), 0)
|
||||
return im, labels
|
||||
|
||||
|
||||
def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n)
|
||||
# Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
|
||||
w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
|
||||
w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
|
||||
ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio
|
||||
return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue