GitLab

* 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

* introduce _check method for type checks on prototype transforms

* cleanup

* Update torchvision/prototype/transforms/_geometry.py
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* introduce _check on new transforms

* _check -> _check_inputs

* always check inputs in _RandomApplyTransform
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* introduce nearest-exact interpolation

* update prototype tests

* update stable tests

* expand ToDtype to support multiple conversions at once

* simplify

Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* [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

* Use the variable name sizes instead of scales for consistency

* Add the missing type hints

* Restore the naming back to scales instead of sizes to avoid backwards incompatibility

* Add video support on MixUp and CutMix

* Switch back to roll

* Fix tests and mypy

* Another mypy fix

* 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

* close streams in prototype datasets

* refactor prototype SBD to avoid closing demux streams at construction time

* mypy

* Fix windows python 3.8

* Update torchvision/extension.py
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Update torchvision/extension.py
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* 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

* pad_image_tensor

* pad_mask and pad_bounding_box

* resize_{image_tensor, mask, bounding_box}

* center_crop_{image_tensor, mask}

* {five, ten}_crop_image_tensor

* crop_{image_tensor, mask}

* convert_color_space_image_tensor

* affine_{image_tensor, mask, bounding_box}

* rotate_{image_tensor, mask}

* gaussian_blur_image_tensor

* cleanup

* Add ValueError

* Add tests for ValueError

* Add tests for ValueError

* Add ValueError

* Change to if/else

* Ammend iou_fn tests

* Move code excerpt

* Format tests
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Rephrase ONNX RoiAlign warning for aligned=True

* add comma
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>