* Switch default LR scheduler from cos to linear

Based on empirical results of training both ways on all YOLOv5 models.

* linear bug fix

* GH: add PR template

* Update CONTRIBUTING.md

* Update PULL_REQUEST_TEMPLATE.md

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

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

* Update PULL_REQUEST_TEMPLATE.md

* Update PULL_REQUEST_TEMPLATE.md

* Update PULL_REQUEST_TEMPLATE.md

* Update PULL_REQUEST_TEMPLATE.md
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>

This is a torch bug, but they seem unable or unwilling to fix it so I'm creating a suppression in YOLOv5. 

Resolves https://github.com/ultralytics/yolov5/issues/6692

* Use `export_formats()` in export.py

* list fix

* refactor: use edgetpu flag

* fix: remove bitwise and assignation to tflite

* Cleanup and fix tflite

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

Integer division by a float yields a (rounded) float. This causes
the dataloader to crash when creating a range.

* Fix CoreML P6 inference

* [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 exporting saved_model: pb exceeds 2GB

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

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

* Replace TF v1.x API with TF v2.x API for saved_model export

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

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

* Clean up

* Remove lambda in tf.function()

* Revert "Remove lambda in tf.function()" to be compatible with TF v2.4

This reverts commit 46c7931f11dfdea6ae340c77287c35c30b9e0779.

* Fix for pre-commit.ci

* Cleanup1

* Cleanup2

* Backwards compatibility update

* Update common.py

* Update common.py

* Cleanup3
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>

Revert to 21.10 on autobuild fail

Reordered installation may help reduce resource usage in autobuild

Also `nvidia-tensorboard-plugin-dlprof`, `nvidia-tensorboard` are no longer installed in NVCR base.

22.10 returns 'no space left on device' error message.

Seems like a bug at docker. Raised issue in https://github.com/docker/hub-feedback/issues/2209

* Handle `scipy.cluster.vq.kmeans` too few points

Resolves #6664

* Update autoanchor.py

* Cleanup

New `--cache val` argument will cache validation set only into RAM. Should help multi-GPU training speeds without consuming as much RAM as full `--cache ram`.

Fix for #6658 for single-GPU and CPU training use cases

Per https://github.com/ultralytics/yolov3/issues/1887#issuecomment-1041135181

Fix attempt for https://github.com/ultralytics/yolov5/issues/6626

* Add benchmarks.py

* Update

* Add requirements

* Updates

* Updates

* Updates

* Updates

* Updates

* Updates

* dataset autodownload from root

* Update

* Redirect to /dev/null

* sudo --help

* Cleanup

* Add exports pd df

* Updates

* Updates

* Updates

* Cleanup

* dir handling fix

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

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

* Cleanup

* Cleanup2

* Cleanup3

* Cleanup model_type
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* log best.pt metrics at train end

* update

* Update __init__.py

* flush callbacks when using evolve

* remember batch size on resuming

* Update train.py

* improve stability of resume
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Per https://github.com/ultralytics/yolov5/issues/5860#issuecomment-1035320018 by @hdnh2006

* Fix missing data folder when running log_dataset

* Use ROOT/'data'

* PEP8 whitespace

* Fix `hyp_evolve.yaml` indexing bug

Bug caused hyp_evolve.yaml to display latest generation result rather than best generation result.

* Update plots.py

* Update general.py

* Update general.py

* Update general.py

Per https://github.com/ultralytics/yolov5/issues/6583#issuecomment-1034421945 by @alicera

* Update train.py

As see in #6463, modification on train in evolve process to allow custom save directory.

* fix val

* PEP8

whitespace around operator

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

* Fix `plot_labels()` colored histogram bug

* Cleanup

* Fix zero-export handling with `if any(f):`

Partial fix for https://github.com/ultralytics/yolov5/issues/6563

* Cleanup

* Improved AutoBatch DDP error message

* Cleanup

* Move trainloader functions to class methods

* results = ThreadPool(NUM_THREADS).imap(self.load_image, range(n))

* Cleanup

* Edge TPU TF imports fix

Fix for https://github.com/ultralytics/yolov5/issues/6535#issuecomment-1030631526

* Update common.py