* Update torch_utils.py

* Additional code refactoring

* tuples to sets

* Cleanup

* CLI fire prep updates

* revert unintentional TF export change

* DetectMultiBackend() `--half` handling

* CI fixes

* rename .half to .fp16 to avoid conflict

* warmup fix

* val update

* engine update

* engine update

* Add detect.py GIF video inference

* Cleanup

* Add Apple CoreML inference

* Cleanup

* Global export sort

* Cleanup

* fix imgsz bug

* Update detect.py

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

* Refactor new `model.warmup()` method

* Add half

* Fix float zeros format

* 255 to integer

`check_requirements()` is unreliable for large packages like torch and tensorflow that may have multiple installation routes (i.e. conda, pip, tensorflow-cpu, etc.)

* Update `set_logging()`

* Update export.py

* pre-commit fixes

* Update LoadImages

* Update LoadStreams

* Update print_args

* Single LOGGER definition

* yolo.py fix

Co-authored-by: pre-commit <pre-commit@example.com>

* Check `'onnxruntime-gpu' if torch.has_cuda`

* fix indent

* update detect.py in order to support torch script

This change assumes the torchscrip file was previously saved with `export.py`

* update `detect.py` for torchscript support

Simple update for torchscript support. Assumes the torchscript file has been generated with `export.py`

* Cleanup

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

* Add OpenCV DNN option for ONNX inference

Usage:

```bash
python detect.py --weights yolov5s.onnx  # ONNX Runtime inference
python detect.py --weights yolov5s.onnx -dnn  # OpenCV DNN inference
```

* DNN prediction to tensor

* Update detect.py

* use os.path.relpath instead of relative_to

* use os.path.relpath instead of relative_to

* Remove os.path from val.py

* Remove os.path from train.py

* Update detect.py import to os

* Update export.py import to os

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

* Allow YOLOv5 execution from arbitrary `cwd`

* Fix str bugs

* Automatic Chinese fonts plotting

* Default PIL=False

* Simplify `check_requirements()` usage

* remove assert, print()

* Update `sys.path.append(str(ROOT))`

* Cleanup

* Refactor argparser printing to `print_args()`

* Cleanup

* 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

* Improved detect.py timing

* Eliminate 1 time_sync() call

* Inference-only time

* dash

* #Save section

* Cleanup

* Add suffix checks

* Cleanup

* Cleanup2

* Cleanup3

* 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

* 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>