GitLab

* Test: add backend parameter

* VideoReader object now works on backend

* Frame reading now passes

* Keyframe seek now passes

* Pyav backend now supports metadata

* changes in test to reflect GPU decoder change

* Linter?

* Test GPU output

* Addressing Joao's comments

* lint

* lint

* Revert "Test GPU output"

This reverts commit f62e955d7dc81bcb23b40d58ea75413b9b62e76d.

* lint?

* lint

* lint

* Address issues in build?

* hopefully doc fix

* Arrgh

* arrgh

* fix typos

* fix input options

* remove read from memory option in pyav

* skip read from mem test for gpu and pyab be

* fix test

* remove unused import

* Hack to get reading from memory work with pyav

* patch audio test
Co-authored-by: Bruno Korbar <bkorbar@quansight.com>
Co-authored-by: Joao Gomes <jdsgomes@fb.com>

* Add support of inplace on `convert_format_bounding_box`

* Move `as_subclass` calls to `F` invocations

* Fix bug.

* Fix _cxcywh_to_xyxy.

* Fixing _xyxy_to_cxcywh.

* Adding comments.

* extend support of posterize to all integer and floating dtypes

* remove raise

* revert to fixed value range for integer dtypes

* extend equalize to all integer and floating dtypes

* address nits

Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* style: Fixed typing of dataset __getitem__

* style: Fixed last missing typing
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Change random generator for ColorJitter.

* Move `_convert_fill_arg` from runtime to constructor.

* Remove unnecessary TypeVars.

* Remove unnecessary casts

* Update comments.

* Minor code-quality changes on Geometical Transforms.

* Fixing linter and other minor fixes.

* Change mitigation for mypy.`

* Fixing the tests.

* Fixing the tests.

* Fix linter

* Restore dict copy.

* Handling of defaultdicts

* restore int idiom

* Update todo

* Moving value estimation of `RandomErasing` from runtime to constructor.

* Speed up mixing on MixUp/Cutmix and small optimization on SimpleCopyPaste.

* Apply nits.

* Minor improvements on functional.

* Restore `_split_alpha`.

* Revert "Restore `_split_alpha`."

This reverts commit 2286120be6d4af2a3c9b52b605d87611ec70fe06.

* Clean ups on `features` area

* remove unncessary imports

* unwrap features in dispatchers

* cleanup

* align erase / five_crop / ten_crop with other dispatchers

* Cleaning up the size dimension methods.

* Change error messages.

* Avoid GPU-CPU sync on Normalize

* Further optimizations.

* Apply code review changes.

* Fixing JIT.

* linter fix

* improve performance of invert_image_tensor

* cleanup

* lint

* more cleanup

* use new invert in solarize

* Speed improvement for adjust gamma op

* Adding comments and optimizations.

* fixing typo

* Remove unnecessary channel check.

* WIP

* Updated rgb2hsv and a bit of hsv2rgb

* Fix issue with batch of images

* Few improvements

* hsv2rgb improvements

* PR review

* another update

* Fix cuda issue with empty images
torch.aminmax is failing
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* WIP

* Updates to speed up autocontrast
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Adding temporal sampling kernel and dispatcher.

* Adding the UniformTemporalSubsample class.

* Add it on init

* Adding tests.

* Addressing comments.

* Reverting proposal as it led to different results.

* add more tests for uniform_temporal_subsample

* cleanup

* fix logic

* fix logic

* make test more strict

* lint

* Update torchvision/prototype/transforms/functional/_temporal.py

* remove pytorchvideo again per request
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* add KernelInfo

* split dtype and device consistency tests

* add proper support for video

* fix tests and add DispatcherInfo

* add aliases

* cleanup

* fix typo

[FBcode->GH]

* remove copy from convert_color_space

* remove copy from convert_format_bounding_box

* remove .to_* methods from features

* remove unnecessary clones

* add perf todos

* refactor convert_color_space

* lint

* remove another clone

* and another clone

* remove a missed copy

* Add PermuteDimensions and TransposeDimensions transforms

* Strip Subclass info.

* Apply changes from code review.

* unwrap features before calling the kernels

* revert double unwrapping

* cleanup

* remove debug raise

* more cleanup

* perf improvements for equalize
Co-authored-by: lezcano <lezcano-93@hotmail.com>

* improve reference tests

* add extensive comments and minor fixes to the kernel

* improve comments
Co-authored-by: lezcano <lezcano-93@hotmail.com>

* WIP

* _blend optim v1

* _blend and color ops optims: v2

* updated a/r tol and configs to make tests pass

* Loose a/r tolerance in AA tests

* Use custom rgb_to_grayscale

* Renamed img -> image

* nit code update

* PR review

* adjust_contrast convert to float32 earlier

* Revert "adjust_contrast convert to float32 earlier"

This reverts commit a82cf8c739d02acd9868ebee4b8b99d101c3e45e.

* add tensor as optional param

* add init from memory

* fix bug

* fix bug

* first working version

* apply formatting and add tests

* simplify tests

* fix tests

* fix wrong variable name

* add path as optional parameter

* add src as optional

* address pr comments

* Fix warning messages

* address pr comments

* make tests stricter

* Revert "make tests stricter"

This reverts commit 6c92e94e8372f381c9496c9f885c2c71b6a4356b.

* improve perf on convert_image_dtype and add tests

* add reference tests

* use bitshifts for int to int

* revert bitshifts for int to int upscale

* fix warning ignore

* fix, ignore, or assert warnings for consistency tests

* fix, ignore, or assert warnings for kernel infos

* fix to_image_tensor for numpy inputs

* make image from numpy contiguous

* fix test

* Add raft_stereo weights

* Update the metrics layout

* Use softmax in _get_gaussian_kernel1d

* Revert "Use softmax in _get_gaussian_kernel1d"

This reverts commit eb8fba36302d2da9e06e6f40afaaf901b276a771.

* Code update

* Relaxed tolerance in consistency tests for GaussianBlur and ElasticTransform

* Code review updates

* Update test_prototype_transforms_consistency.py

* [proto] Reduce number of calls of __torch_function__

* Use DisableTorchFunction and super

* Use self._tensor

* Fixes mypy and color space handling

* revert Image.new_like

* WIP

* Perf opt with ref to tensor and properties

* Removed requires_grad property

* Use _tensor ref

* Revert "Use _tensor ref"

This reverts commit 38f8e21242830fed46ddf31287edb67c1abd124a.

* Update torchvision/prototype/features/_feature.py
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Fix `ToDtype` to avoid errors when a type is not defined.

* Nit `(features.is_simple_tensor, features._Feature)` to `(Tensor,)`

* Fixing linter

* Adding comment.

* Switch back to indexing. Python's default dict seems to have a nasty behaviour.

* Extend RandomShortestSize to support Video specific flavour of the augmentation

* Adding a test.

* Apply changes from code review