GitLab

* [proto][tests] Added ref functions for h/v flips

* Better dtype handling in reference_affine_bounding_box_helper

* [proto] Speed-up h/v bboxes flip ops

* Use more inplace ops

* Removed _old methods

* Fixed jit issue using a bit slower version

* 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

* 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

* 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

* 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

* 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.

* 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

* 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] Performance improvements for equalize op

* Added tests

* Removing unnecessary methods/classes.

* Unions instead of ImageOrVideo types

* Fixing JIT issue.

* [proto] Small improvement for tensor equalize op

* Fix code formatting

* Added a comment on the ops

* Change `image_size` to `spatial_size`

* Fix linter

* Fixing more tests.

* Adding get_num_channels_video and get_spatial_size_* kernels for video, masks and bboxes.

* Refactor get_spatial_size

* Reduce the usage of `query_chw` where possible

* Rename `query_chw` to `query_spatial_size`

* Adding `get_num_frames` dispatcher and kernel.

* Adding jit-scriptability tests

* Adding support of Video to missed Transforms and Kernels

* Fixing Grayscale Transform.

* Fixing FiveCrop and TenCrop Transforms.

* Fix Linter

* Fix more kernels.

* Add `five_crop_video` and `ten_crop_video` kernels

* Added a TODO.

* Missed Video isinstance

* nits

* Fix bug on AugMix

* Nits and TODOs.

* Reapply Philip's recommendation

* Fix mypy and JIT

* Fixing test

* Remove performance workaround for mask resize

* Fix linter

* bug fixes

* remove unnecessary import

* Fixing linter

* enable arbitrary batch size for all prototype kernels

* put back perspective dispatcher

* Rewrite `get_dimensions`, `get_num_channels` and `get_spatial_size`

* Remove `get_chw`

* Remove comments

* Make `get_spatial_size` support non-image input

* Reduce the unnecessary use of `get_dimensions*`

* Fix linters

* Fix merge bug

* Linter

* Fix linter

* replace new_like with wrap_like

* fix videos

* revert casting in favor of ignoring mypy

* add video feature

* add video kernels

* add video testing utils

* add one kernel info

* fix kernel names in Video feature

* use only uint8 for video testing

* require at least 4 dims for Video feature

* add TODO for image_size -> spatial_size

* image -> video in feature constructor

* introduce new combined images and video type

* add video to transform utils

* fix transforms test

* fix auto augment

* cleanup

* address review comments

* add remaining video kernel infos

* add batch dimension squashing to some kernels

* fix tests and kernel infos

* add xfails for arbitrary batch sizes on some kernels

* fix test setup

* fix equalize_image_tensor for multi batch dims

* fix adjust_sharpness_image_tensor for multi batch dims

* address review comments

* Avoid recommuting the affine matrix in bbox rotate

* Fix linter

* inverted=True for estimating image size

* Update the image size estimation to match the one from the image kernel

* Nits

* Address comments.

* Center=0,0 when expand=true

* prevent feature wrapping for inplace ops

* cleanup

* mypy

* refactor __torch_function__ to be more concise

* avoid double lookup

* fix normalize

* refactor normalize

* mypy