* track batch size after autobatch

* remove redundant import

* Update __init__.py

* Update __init__.py

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

Slightly more efficient than .to(device)

Consider that the default value is CIOU，adjust the order of judgment could reduce the number of judgments.
And “elif CIoU:” didn't need 'if'.

Co-authored-by: 李杰 <360751194@qq.comqq.com>

* OpenVINO export

* Remove timeout

* Add 3 files

* str

* Constrain opset to 12

* Default ONNX opset to 12

* Make dir

* Make dir

* Cleanup

* Cleanup

* check_requirements(('openvino-dev',))

* support specfiy multiple frozen layers

* fix bug

* Cleanup Freeze section

* Cleanup argument

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

* Making `ar_thr` available as a hyperparameter

* Disabling ar_thr as hyperparameter and computing from the dataset instead

* Fixing bug in ar_thr computation

* Fix `ar_thr` to 100

Add __init__() function.

* fix imgsz bug

* Update detect.py

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

* add nms and agnostic nms to export.py

* fix agnostic implies nms

* reorder args to group TF args

* PEP8 120 char

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

Replace 'training_result' with 'best_fitness' in strip_optimizer() to match key with ckpt from train.py

* fix .gitignore not tracking existing folders

fix .gitignore so that the files that are in the repository are actually being tracked.

Everything in the data/ folder is ignored, which also means the subdirectories are ignored. Fix so that the subdirectories and their contents are still tracked.

* Remove data/trainings

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

* Find out a bug. When set batch_size = -1 to use the autobatch.

reproduce:

* Fix type conflict

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

* Add *.engine (TensorRT extensions) to .gitignore

* Update .dockerignore

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

debugged for missigned Detections attributes

* Export multiple models in series

Export multiple models in series by adding additional `*.pt` files to the `--weights` argument, i.e.:

```bash
python export.py --include tflite --weights yolov5n.pt  # export 1 model
python export.py --include tflite --weights yolov5n.pt yolov5s.pt yolov5m.pt yolov5l.pt yolov5x.pt  # export 5 models
```

* Update export.py

* Update README.md

* Update AutoShape()

* autodownload ONNX

* Cleanup

* Finish updates

* Add Usage

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* fix device

* Update hubconf.py

* Update common.py

* smart param selection

* autodownload all formats

* autopad only pytorch models

* new_shape edits

* stride tensor fix

* Cleanup

shallow copy modify originals

* Update val.py

Add an option to choose number of workers if not called by train.py

* Update comment

* 120 char line width

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

* Update val.py

Solving Non-ASCII character '\xf0' error during runtime

* Update val.py

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

Video errors may occur.

When OpenCV retrieving image fail, original code would modify source images **inplace**, which may result in plotting bounding boxes on a black image. That is, before inference, source image `im0s[i]` is OK, but after inference before `Process predictions`,  `im0s[i]` may have been changed.

* `try: except (..., wandb.errors.UsageError)`

* bug fix

* feat: change file suffix in pythonic way

* fix: enforce binding addresses order

* fix: enforce binding addresses order

* Refactor new `model.warmup()` method

* Add half