GitLab

* add ufmt as code formatter

* cleanup

* quote ufmt requirement

* split imports into more groups

* regenerate circleci config

* fix CI

* clarify local testing utils section

* use ufmt pre-commit hook

* split relative imports into local category

* Revert "split relative imports into local category"

This reverts commit f2e224cde2008c56c9347c1f69746d39065cdd51.

* pin black and usort dependencies

* fix local test utils detection

* fix ufmt rev

* add reference utils to local category

* fix usort config

* remove custom categories sorting

* Run pre-commit without fixing flake8

* got a double import in merge
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* Adding ExponentialLR and LinearLR

* Fix arg type of --lr-warmup-decay

* Adding support of Zero gamma BN and SGD with nesterov.

* Fix --lr-warmup-decay for video_classification.

* Update bn_reinit

* Fix pre-existing bug on num_classes of model

* Remove zero gamma.

* Use fstrings.

* Warmup on Classficiation references.

* Adjust epochs for cosine.

* Warmup on Segmentation references.

* Warmup on Video classification references.

* Adding support of both types of warmup in segmentation.

* Use LinearLR in detection.

* Fix deprecation warning.

* Adding presets in the classification reference scripts.

* Adding presets in the object detection reference scripts.

* Adding presets in the segmentation reference scripts.

* Adding presets in the video classification reference scripts.

* Moving flip at the end to align with image classification signature.

* [WIP] Update ref example video classification

* [WIP] Updated video classification ref example

* Replaced mem format conversion functions by classes

* remove sys.version_info == 2

* remove sys.version_info < 3

* remove from __future__ imports

* Generalised for custom dataset

* Typo, redundant code, sensible default

* Args for name of train and val dir

* move sampler into TV core. Update UniformClipSampler

* Fix reference training script

* Skip test if pyav not available

* change interpolation from round() to floor() as round(0.5) behaves differently between py2 and py3

* [WIP] Minor cleanups on R3d

* Move all models to video/resnet.py

* Remove old files

* Make tests less memory intensive

* Lint

* Fix typo and add pretraing arg to training script

* Move RandomClipSampler to references

* Lint and bugfix

Also add docs

* Copy classification scripts for video classification

* Initial version of video classification

* add version

* Training of r2plus1d_18 on kinetics work

Gives even slightly better results than expected, with 57.336 top1 clip accuracy. But we count some clips twice in this evaluation

* Cleanups on training script

* Lint

* Minor improvements

* Remove some hacks

* Lint

* adding mixed precision training with Apex

* fix APEX default optimization level

* adding python version check for apex

* fix LINT errors and raise exceptions if apex not available

* fixing apex distributed training

* fix throughput calculation: include forward pass

* remove torch.cuda.set_device(args.gpu) as it's already called in init_distributed_mode

* fix linter: new line

* move Apex initialization code back to the beginning of main

* move apex initialization to before lr_scheduler - for peace of mind. Though, doing apex initialization after lr_scheduler seems to work fine as well

* adding mixed precision training with Apex

* fix APEX default optimization level

* adding python version check for apex

* fix LINT errors and raise exceptions if apex not available

Allows for easily evaluating the pre-trained models in the modelzoo

* Miscellaneous improvements to the classification reference scritps

* Fix lint

* Add groups support to ResNet

* Kill BaseResNet

* Make it support multi-machine training

Making references/classification/train.py and references/classification/utils.py  compatible with python2  (#831)

* linter fixes

* linter fixes

* Initial version of classification reference training script

* Updates

* Minor updates

* Expose a few more options

* Load optimizer and lr_scheduler when resuming

Also log the learning rate

* Evaluation-only and minor improvements

Identified a bug in the reporting of the results. They need to be reduced between all processes

* Address Soumith's comment

* Fix some approximations on the evaluation metric

* Flake8