* evolve fix

* Enable login timeout

* fix pkg

* check rank

* don't relogin

* fix

* reformat

* evolve fix

* Enable login timeout

* fix pkg

* check rank

* don't relogin

* Annotator `check_font()` RANK -1 remove progress

* Cleanup

* Simplify `check_requirements()` usage

* remove assert, print()

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

* Cleanup

* Refactor argparser printing to `print_args()`

* Cleanup

* evolve fix

* Enable login timeout

* fix pkg

PR should produce datasets sorted alphabetically by filename. Cache version incremented to 0.5. 

Note: will force a one-time re-caching of existing datasets on first-use.

* Unpin Pillow

* Update requirements.txt

* Update plots.py

* Fix val.py study plot

* call plot_val_study

* Rename plot_study_txt to plot_val_study

* added callbacks

* added back callback to main

* added save_dir to callback output

* merged in upstream

* removed ghost code

* added url check

* Add url2file()

* Update file-only

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

Thank you for sharing nice open-source codes 👍

I applied to shuffle the order of all 4(or 9) images in mosaic augmentation

Currently, the order of images in mosaic augmentation is not completely random.
The remaining images except the first are randomly arranged. Apply shuffle all to increase the diversity of data composition.

* 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

* Writeable test

* Fix

* Cleanup

* Fix `is_writeable()` for 3 OS support

* Update general.py

* Add `user_config_dir`

* Linux to .config

* Update `check_yaml()` comment

* Cleanup

Fix a bug when `file=''`

* Add suffix checks

* Cleanup

* Cleanup2

* Cleanup3

* added callbacks

* added back callback to main

* added save_dir to callback output

* reduced code count

* updated callbacks

* added default callback class to main, added missing parameters to on_model_save

* Glenn updates

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

* Remove assert

* debug0

* trace=not opt.sync

* sync to sync_bn fix

* Cleanup

* Close plots

* Replace fig.close() for plt.close()

* Auto-download Arial.ttf on init

* Fix ROOT

* 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 `Profile()` profiler

* CamelCase Timeout

* Add EarlyStopping feature

* Add comment

* Cleanup

* Cleanup2

* debug

* debug2

* debug3

* debug3

* debug4

* debug5

* debug6

* debug7

* debug8

* debug9

* debug10

* debug11

* debug12

* Cleanup

* Add TODO for known DDP issue

Auto-fix corrupt JPEGs PR introduced a bug whereby the f.seek() operation read all of the bytes in the image, resulting in the PIL image having nothing to read upon the .save() operation. 

Fix was to re-open the image using PIL before saving.

* Autofix corrupt JPEGs

This PR automatically re-saves corrupt JPEGs and trains with the resaved images. WARNING: this will overwrite the existing corrupt JPEGs in a dataset and replace them with correct JPEGs, though the filesize may increase and the image contents may not be exactly the same due to lossy JPEG compression schemes. Results may vary by JPEG decoder and hardware.

Current behavior is to exclude corrupt JPEGs from training with a warning to the user, but many users have been complaining about large parts of their dataset being excluded from training.

* Clarify re-save reason

* Add `install=True` argument to `check_requirements`

* Update general.py