* set common default stride as 32

* restore default stride, and set it on argument optional

* fix wrong use of opt

* fix missing parameter of stride

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix format of parameters

* Update val.py

* Update common.py
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Test exports

* Fix precommit

* Print dataset scan only `if RANK in (-1, 0)`

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ciCo-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* Simplify callbacks.py return

* Indent args (pytorch convention)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ciCo-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Updated dataset size to 712GB (includes undeleted zips).

* Copy wandb param dict before training to avoid overwrites.

Copy the hyperparameter dict retrieved from wandb configuration before passing it to `train()`. Training overwrites parameters in the dictionary (eg scaling obj/box/cls gains), which causes the values reported in wandb to not match the input values. This is confusing as it makes it hard to reproduce a run, and also throws off wandb's Bayesian sweep algorithm.

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

* Add `on_train_start()` callback

* Update

* Update

* Add `retry=3` to `download()`

* Update general.py

* Update general.py

* Update general.py

* Update VOC.yaml

* Update VisDrone.yaml

* Update export.py

Simplify code.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ciCo-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* fix: disable usage of root logger

`logging.basicConfig` configures Python's root logger. This prohibits
fine control of logging, overwrites logging configuration done outside
the package, and is not best practice. Instead, the used logger is now
configured directly, and the root logger is untouched.

Example:
    If yolov5 is used as part of another project with some sophisticated
    logging, the internal `logging.basicConfig` call overwrites all the
    external configuration.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update general.py

* Update general.py

* Comment kaggle

* Uncomment kaggle
Co-authored-by: Maximilian Strobel <Maximilian.Strobel@infineon.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Add  `check_requirements(('pycocotools>=2.0',))`

Improved error messages for understanding of user error with val.py. May help https://github.com/ultralytics/yolov5/issues/7291

* Flask context manager `open()` fix

* Additional read context manager fixes

* enable TensorFlow ops if flag --nms or --agnostic-nms is used

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update export.py

* Update export.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ciCo-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* [pre-commit.ci] pre-commit suggestions

updates:
- [github.com/asottile/pyupgrade: v2.31.0 → v2.31.1](https://github.com/asottile/pyupgrade/compare/v2.31.0...v2.31.1)
- [github.com/pre-commit/mirrors-yapf: v0.31.0 → v0.32.0](https://github.com/pre-commit/mirrors-yapf/compare/v0.31.0...v0.32.0)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update yolo.py

* Update activations.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update activations.py

* Update tf.py

* Update tf.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ciCo-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Eliminate 1 op during training and inference.

* Update

* Update

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ciCo-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* Update

* Update time_limit

* Update restapi.py

* Update restapi.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ciCo-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Resolve `UserWarning: Usage of dash-separated 'description-file' will not be supported in future versions. Please use the underscore name 'description_file' instead`

* Fix `www.youtube.com` hostname

* Update datasets.py

* SavedModel TF Serve Fix

Fix for https://github.com/ultralytics/yolov5/issues/7205 proposed by @tylertroy

* Update export.py