a2d617ece9
Update loss for FP16 `tobj` ( #7088 )
il y a 2 ans
6f128031d0
Update loss.py with `if self.gr < 1:` ( #7087 )
* Update loss.py with `if self.gr < 1:`
* Update loss.py
il y a 2 ans
9b771a3e71
Revert "Update detect.py non-inplace with `y.tensor_split()` ( #7062 )" ( #7074 )
This reverts commit d5e363f29d
il y a 2 ans
9cd89b75cc
Fix2 `check_anchor_order()` in pixel-space not grid-space ( #7067 )
Follows https://github.com/ultralytics/yolov5/pull/7060 which provided only a partial solution to this issue. #7060 resolved occurences in yolo.py, this applies the same fix in autoanchor.py.
il y a 2 ans
178c109576
Add non-zero `da` `check_anchor_order()` condition ( #7066 )
il y a 2 ans
9e75cbf4c1
Update __init__.py ( #7065 )
il y a 2 ans
e278fd63ec
Update W&B message to `LOGGER.info()` ( #7064 )
il y a 2 ans
0529b77232
Update common.py lists for tuples ( #7063 )
Improved profiling.
il y a 2 ans
d5e363f29d
Update detect.py non-inplace with `y.tensor_split()` ( #7062 )
il y a 2 ans
f327eee614
Fix `check_anchor_order()` in pixel-space not grid-space ( #7060 )
* Update `check_anchor_order()`
Use mean area per output layer for added stability.
* Check in pixel-space not grid-space fix
il y a 2 ans
529fbc1814
Use PIL to eliminate chroma subsampling in crops ( #7008 )
* use pillow to save higher-quality jpg (w/o color subsampling)
* Cleanup and doc issue
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
il y a 2 ans
9f4d11379b
Fix incomplete URL substring sanitation ( #7056 )
Resolves code scanning alert in https://github.com/ultralytics/yolov5/issues/7055
il y a 2 ans
6843ea5d7f
Create SECURITY.md ( #7054 )
* Create SECURITY.md
Resolves https://github.com/ultralytics/yolov5/issues/7052
* Move into ./github
* Update SECURITY.md
il y a 2 ans
9ebec7885f
Update Dockerfile to `git clone` instead of `COPY` ( #7053 )
Resolves git command errors that currently happen in image, i.e.:
```bash
root@382ae64aeca2:/usr/src/app# git pull
Warning: Permanently added the ECDSA host key for IP address '140.82.113.3' to the list of known hosts.
git@github.com: Permission denied (publickey).
fatal: Could not read from remote repository.
Please make sure you have the correct access rights
and the repository exists.
```
il y a 2 ans
b0ba101ac0
`ComputeLoss()` indexing/speed improvements ( #7048 )
* device as class attribute
* Update loss.py
* Update loss.py
* improve zeros
* tensor split
il y a 2 ans
4effd064b1
Consistent saved_model output format ( #7032 )
il y a 2 ans
7c6a33564a
fix: add default PIL font as fallback ( #7010 )
* fix: add default font as fallback
Add default font as fallback if the downloading of the Arial.ttf font
fails for some reason, e.g. no access to public internet.
* Update plots.py
Co-authored-by: Maximilian Strobel <Maximilian.Strobel@infineon.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
il y a 2 ans
3f634d43c8
Conditional `Timeout()` by OS (disable on Windows) ( #7013 )
* Conditional `Timeout()` by OS (disable on Windows)
* Update general.py
il y a 2 ans
c09fb2aa95
Update TQDM bar format ( #6988 )
il y a 2 ans
932dc78496
YOLOv5 Export Benchmarks for GPU ( #6963 )
* Add benchmarks.py GPU support
* Updates
* Updates
* Updates
* Updates
* Add --half
* Add TRT requirements
* Cleanup
* Add TF to warmup types
* Update export.py
* Update export.py
* Update benchmarks.py
il y a 2 ans
99de551f97
pt model to cpu on TF export
il y a 2 ans
2d45de617e
Model `ema` key backward compatibility fix ( #6972 )
Fix for older model loading issue in d3d9cbce22 (commitcomment-68622388)
il y a 2 ans
c13d4ce7ef
EdgeTPU optimizations ( #6808 )
* removed transpose op for better edgetpu support
* fix for training case
* enabled experimental new quantizer flag
* precalculate add and mul ops at compile time
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
il y a 2 ans
701e1177ac
Tensor initialization on device improvements ( #6959 )
* Update common.py speed improvements
Eliminate .to() ops where possible for reduced data transfer overhead. Primarily affects warmup and PyTorch Hub inference.
* Updates
* Updates
* Update detect.py
* Update val.py
il y a 2 ans
52c1399fdc
DetectMultiBackend() return `device` update ( #6958 )
Fixes ONNX validation that returns outputs on CPU.
il y a 2 ans
c84dd27d62
New val.py `cuda` variable ( #6957 )
* New val.py `cuda` variable
Fix for ONNX GPU val.
* Update val.py
il y a 2 ans
c6b4f84fd1
Update Dockerfile `torch==1.11.0+cu113` ( #6954 )
il y a 2 ans
b94b59e199
DetectMultiBackend() `--half` handling ( #6945 )
* DetectMultiBackend() `--half` handling
* CI fixes
* rename .half to .fp16 to avoid conflict
* warmup fix
* val update
* engine update
* engine update
il y a 2 ans
84efa62b2d
Fix PyTorch Hub export inference shapes ( #6949 )
May resolve https://github.com/ultralytics/yolov5/issues/6947
il y a 2 ans
caf7ad0500
Allow 3-point segments ( #6938 )
May resolve https://github.com/ultralytics/yolov5/issues/6931
il y a 2 ans
055e72af5b
Optimize PyTorch 1.11.0 compatibility update ( #6933 )
il y a 2 ans
d3d9cbce22
PyTorch 1.11.0 compatibility updates ( #6932 )
Resolves `AttributeError: 'Upsample' object has no attribute 'recompute_scale_factor'` first raised in https://github.com/ultralytics/yolov5/issues/5499
il y a 2 ans
6dd82c0252
Move `git_describe()` to general.py ( #6918 )
* Move `git_describe()` to general.py
* Move `git_describe()` to general.py
il y a 2 ans
e6e36aac10
Update bytes to GB with bitshift ( #6886 )
il y a 2 ans
acc58c1dcf
Fix TRT `max_workspace_size` deprecation notice ( #6856 )
* Fix TRT `max_workspace_size` deprecation notice
* Update export.py
* Update export.py
il y a 2 ans
a5a1760ea6
Bump actions/checkout from 2 to 3 ( #6881 )
Bumps [actions/checkout](https://github.com/actions/checkout ) from 2 to 3.
- [Release notes](https://github.com/actions/checkout/releases )
- [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md )
- [Commits](https://github.com/actions/checkout/compare/v2...v3 )
---
updated-dependencies:
- dependency-name: actions/checkout
dependency-type: direct:production
update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
il y a 2 ans
c8a589920e
Bump actions/setup-python from 2 to 3 ( #6880 )
Bumps [actions/setup-python](https://github.com/actions/setup-python ) from 2 to 3.
- [Release notes](https://github.com/actions/setup-python/releases )
- [Commits](https://github.com/actions/setup-python/compare/v2...v3 )
---
updated-dependencies:
- dependency-name: actions/setup-python
dependency-type: direct:production
update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
il y a 2 ans
596de6d5a0
Default FP16 TensorRT export ( #6798 )
* Assert engine precision #6777
* Default to FP32 inputs for TensorRT engines
* Default to FP16 TensorRT exports #6777
* Remove wrong line #6777
* Automatically adjust detect.py input precision #6777
* Automatically adjust val.py input precision #6777
* Add missing colon
* Cleanup
* Cleanup
* Remove default trt_fp16_input definition
* Experiment
* Reorder detect.py if statement to after half checks
* Update common.py
* Update export.py
* Cleanup
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
il y a 2 ans
7e98b4801a
Update yolov5s.yaml ( #6865 )
* Update yolov5s.yaml
* Update yolov5s.yaml
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
il y a 2 ans
4728840745
Update `--cache disk` deprecate `*_npy/` dirs ( #6876 )
* Updates
* Updates
* Updates
* Updates
* Updates
* Updates
* Updates
* Updates
* Updates
* Updates
* Cleanup
* Cleanup
il y a 2 ans
8a66ebad44
Add `*.ts` to `VID_FORMATS` ( #6859 )
il y a 2 ans
601dbb83f0
AutoAnchor improved initialization robustness ( #6854 )
* Update AutoAnchor
* Update AutoAnchor
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
il y a 2 ans
bcc92e2169
Update sweep.yaml ( #6825 )
* Update sweep.yaml
Changed focal loss gamma search range between 1 and 4
* Update sweep.yaml
lowered the min value to match default
il y a 2 ans
63ddb6f0d0
Update autoanchor.py ( #6794 )
* Update autoanchor.py
* Update autoanchor.py
il y a 2 ans
c2403eb04c
Update PULL_REQUEST_TEMPLATE.md ( #6783 )
il y a 2 ans
9ec51a6396
YOLOv5s6 params FLOPs fix ( #6782 )
il y a 2 ans
0f819919ad
Update EMA decay `tau` ( #6769 )
* Update EMA
* Update EMA
* ratio invert
* fix ratio invert
* fix2 ratio invert
* warmup iterations to 100
* ema_k
* implement tau
* implement tau
il y a 2 ans
b2adc7c39a
Fix export for 1-channel images ( #6780 )
Export failed for 1-channel input shape, 1-liner fix
il y a 2 ans
cea994b3f6
Update hyp.VOC.yaml ( #6772 )
il y a 2 ans
741cd0eb23
Update tutorial.ipynb ( #6771 )
il y a 2 ans
Glenn Jocher
Philip Gutjahr
Mrinal Jain
Max Strobel
paradigm
dependabot[bot]
DavidB
vnekat
Louis Combaldieu
Louis Combaldieu