* Add fused conv support

* Set all saved_model values to non trainable

* Fix TFLite fp16 model export

* Fix int8 TFLite conversion

* Initial commit

* Remove unused export_torchscript return

* ROOT variable

* Add prefix to fcn arg

* fix ROOT

* check_yaml into run()

* interim fixes

* imgsz=(320, 320)

* Hardcode tf_raw_resize False

* Finish opt elimination

* Update representative_dataset_gen()

* Update export.py with TF methods

* SiLU and GraphDef fixes

* file_size() directory handling feature

* export fixes

* add lambda: to representative_dataset

* Detect training False default

* Fuse false for TF models

* Embed agnostic NMS arguments

* Remove lambda

* TensorFlow.js export success

* Add pb to Usage

* Add *_tfjs_model/ to ignore files

* prepend YOLOv5 to function headers

* Remove end --- comments

* parameterize tfjs export pb file

* update run() data default /ROOT

* update --include help

* update imports

* return ct_model

* Consolidate TFLite export

* pb prerequisite to tfjs

* TF modules CamelCase

* Remove exports from tf.py and cleanup

* pass agnostic NMS arguments

* CI

* CI

* ignore *_web_model/

* Add tensorflow to CI dependencies

* CI tensorflow-cpu

* Update requirements.txt

* Remove tensorflow check_requirement

* CI coreml tfjs

* export only onnx torchscript

* reorder exports torchscript first

* Allow specifying multi_label option for NMS when using torch hub

* Reformat

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* adding get cropped functionality

* Add target logic in existing functions

* Crops cleanup

* Add dictionary keys: conf, cls, box

* Bug fixes - avoid return after first image

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Add suffix checks

* Cleanup

* Cleanup2

* Cleanup3

Layer 21 includes the information of xsmall objects

* Add Annotator() class

* Download Arial

* 2x for loop

* Cleanup

* tuple 2 list

* max_size=1920

* bold logging results to

* tolist()

* im = annotator.im

* PIL save in detect.py

* Smart asarray in detect.py

* revert to cv2.imwrite

* Cleanup

* Return result asarray

* Add `Profile()` profiler

* CamelCase Timeout

* Resize after mosaic

* pillow>=8.0.0

* daemon imwrite

* Add cv2 support

* Remove plot_wh_methods and plot_one_box

* pil=False for hubconf.py annotations

* im.shape bug fix

* colorstr common.py

* join daemons

* Update t.daemon

* Removed daemon saving

Profiling fix copies input to Detect layer to circumvent inplace changes to the feature maps.

* Add models/tf.py for TensorFlow and TFLite export

* Set auto=False for int8 calibration

* Update requirements.txt for TensorFlow and TFLite export

* Read anchors directly from PyTorch weights

* Add --tf-nms to append NMS in TensorFlow SavedModel and GraphDef export

* Remove check_anchor_order, check_file, set_logging from import

* Reformat code and optimize imports

* Autodownload model and check cfg

* update --source path, img-size to 320, single output

* Adjust representative_dataset

* Put representative dataset in tfl_int8 block

* detect.py TF inference

* weights to string

* weights to string

* cleanup tf.py

* Add --dynamic-batch-size

* Add xywh normalization to reduce calibration error

* Update requirements.txt

TensorFlow 2.3.1 -> 2.4.0 to avoid int8 quantization error

* Fix imports

Move C3 from models.experimental to models.common

* Add models/tf.py for TensorFlow and TFLite export

* Set auto=False for int8 calibration

* Update requirements.txt for TensorFlow and TFLite export

* Read anchors directly from PyTorch weights

* Add --tf-nms to append NMS in TensorFlow SavedModel and GraphDef export

* Remove check_anchor_order, check_file, set_logging from import

* Reformat code and optimize imports

* Autodownload model and check cfg

* update --source path, img-size to 320, single output

* Adjust representative_dataset

* detect.py TF inference

* Put representative dataset in tfl_int8 block

* weights to string

* weights to string

* cleanup tf.py

* Add --dynamic-batch-size

* Add xywh normalization to reduce calibration error

* Update requirements.txt

TensorFlow 2.3.1 -> 2.4.0 to avoid int8 quantization error

* Fix imports

Move C3 from models.experimental to models.common

* implement C3() and SiLU()

* Fix reshape dim to support dynamic batching

* Add epsilon argument in tf_BN, which is different between TF and PT

* Set stride to None if not using PyTorch, and do not warmup without PyTorch

* Add list support in check_img_size()

* Add list input support in detect.py

* sys.path.append('./') to run from yolov5/

* Add int8 quantization support for TensorFlow 2.5

* Add get_coco128.sh

* Remove --no-tfl-detect in models/tf.py (Use tf-android-tfl-detect branch for EdgeTPU)

* Update requirements.txt

* Replace torch.load() with attempt_load()

* Update requirements.txt

* Add --tf-raw-resize to set half_pixel_centers=False

* Add --agnostic-nms for TF class-agnostic NMS

* Cleanup after merge

* Cleanup2 after merge

* Cleanup3 after merge

* Add tf.py docstring with credit and usage

* pb saved_model and tflite use only one model in detect.py

* Add use cases in docstring of tf.py

* Remove redundant `stride` definition

* Remove keras direct import

* Fix `check_requirements(('tensorflow>=2.4.1',))`

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Add `SPPF()` layer

* Cleanup

* Add credit

* Implement new headers

* Reformat 1

* Reformat 2

* Reformat 3 - math

* Reformat 4 - yaml

* Merge PIL and OpenCV box plotting functions

* Add ASCII check to plot_one_box

* Cleanup

* Cleanup2

* Add yolov5s-ghost.yaml

* Finish C3Ghost

* Add C3Ghost to list

* Add C3Ghost to number of repeats if statement

* Fixes

* Cleanup

Co-authored-by: yangyuantao <yangyuantao@transai.cn>

* more simpler code for DWConvClass

more simpler code for DWConvClass

* remove DWConv function

* Replace DWConvClass with DWConv

* Add `DWConvClass()`

* Cleanup

* Cleanup2

* PyCharm reformat

* YAML reformat

* Markdown reformat

* Train from `--data path/to/dataset.zip` feature

* Update dataset_stats()

* cleanup

* cleanup2

* Module `super().__init__()`

* remove NMS

* AutoShape PosixPath support

Usage example:

````python
from pathlib import Path

model = ...
file = Path('data/images/zidane.jpg')

results = model(file)
```

* Update common.py

* `Detections()` class `print()` overload

* Update common.py

* fix visualize error

* Revert "fix visualize error"

* add visualise profile

Fix inference from PIL source.

* Feature visualization update

* Save to jpg (faster)

* Save to png

* Update BGR2RGB ops

* speed improvements

* cleanup

* rotating an image according to its exif tag

* Update common.py

* Update datasets.py

* Update datasets.py

faster

* delete extraneous gpg file

* Update common.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Add feature map visualization

Add a feature_visualization function to visualize the mid feature map of the model.

* Update yolo.py

* remove boolean from forward and reorder if statement

* remove print from forward

* General cleanup

* Indent

* Update plots.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Add yolov5/ to path

* rename functions to run()

* cleanup

* rename fix

* CI fix

* cleanup find models/export.py

* Update DDP for `torch.distributed.run`

* Add LOCAL_RANK

* remove opt.local_rank

* backend="gloo|nccl"

* print

* print

* debug

* debug

* os.getenv

* gloo

* gloo

* gloo

* cleanup

* fix getenv

* cleanup

* cleanup destroy

* try nccl

* return opt

* add --local_rank

* add timeout

* add init_method

* gloo

* move destroy

* move destroy

* move print(opt) under if RANK

* destroy only RANK 0

* move destroy inside train()

* restore destroy outside train()

* update print(opt)

* cleanup

* nccl

* gloo with 60 second timeout

* update namespace printing

* Slightly modify CLI execution

This simple change makes it easier to run the primary functions of this
repo (train/detect/test) from within Python. An object which represents
`opt` can be constructed and fed to the `main` function of each of these
modules, rather than having to call the lower level functions directly,
or run the module as a script.

* Update export.py

Add CLI parsing update for more convenient module usage within Python.

Co-authored-by: Lewis Belcher <lb@desupervised.io>

* Refactor models/export.py arguments

* cleanup

* cleanup

* early assert for cpu and half option

early assert for cpu and half option

* Modified comment

Modified comment

* call model.eval() when opt.train is False

call model.eval() when opt.train is False

* single-line if statement

* cleanup

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>