GitLab

* add consistency checks for prototype and legacy transforms

* fix Resize

* [proto] Fix bug with Compose and PR 6504

* Added tests and fixed other bugs

* add aliases for hflip and vflip

* reduce imports from torchvision.transforms in torchvision.prototype.transforms

* add aliases for to_pil_image abd pil_to_tensor

* deprecate to_tensor

* add some FIXME cleanup comments

* address reviews

* add dimension getters

* undeprecate PILToTensor and ToPILImage

* address review

* fix test

* move simple_tensor to features module

* fix test

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

* check full sample in query_bounding_box

* support no bounding boxes in FixedSizeCrop

* fix test

* `to_image_tensor` returns `feature.Image`

* Normalize filters PIL on forward

* decode_image_with_pil returns feature.Image

* Remove sample unpacking from Normalize

* Removing debug method that cause mypy to complain

* adding back helpful comment

* undo change on normalize kernel to maintain the helpful error message to users who use the kernel directly

* unused import

* Move output to CPU before assert_expected

* Fixing `test_detection_model`

* check_device=False

* linter

[proto] Consistent supported/unsupported types handling in LinearTransformation, other perf comments (#6498)

* WIP

* [proto] unformal supported/unsupported types handling in LinearTransformation, other perf comments

* Type fixes and other minor stuff

* fix passtrough on transforms and add dispatchers for five and ten crop

* Revert "cleanup prototype auto augment transforms (#6463)"

This reverts commit d8025b9a

.

* use legacy kernels in deprecated Grayscale and RandomGrayscale transforms

* fix default type for Lambda transform

* fix default type for ToDtype transform

* move simple_tensor to features module

* [skip ci]

* Revert "move simple_tensor to features module"

This reverts commit 7043b6ee3e3b1f6541371a4f2442cfc1fd664e4a.

* cleanup

* reinstate valid AA changes

* address review

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

* Fix pass-through and supported types of Normalize

* update error message on kernel

* Fix linter.

* Fix the tests.

* Update type.

* Update type.

* Remove unnecessary tests for bboxes and masks.

* add CUDA11.7 builds

* add CUDA 11.7 builds

* run regenerate.py

* try to add filters to binary_win_conda_py3.10_cu117

* rerun regenerate.py

* Removing conda-forge adding cu117 to windows unit tests

* Debug code

* Remove debug code
Co-authored-by: atalman <atalman@fb.com>

[proto] Use the proper `_transformed_types` in all Transforms and eliminate unnecessary dispatching (#6494)

* Update types in deprecated transforms.

* Update types in type conversion transforms.

* Fixing types in meta transforms.

* More changes on type conversion.

* Bug fix.

* Fix types

* Remove unnecessary conversions.

* Remove unnecessary import.

* Fixing tests

* Remove copy support from `to_image_tensor`

* restore test param

* Fix further tests

* [proto] Updated tests for CopyPaste on OneHotLabel

* Fixing test error

* Fixes unexpected behaviour with Transform._transformed_types and torch.Tensor

* Make code consistent to has_any, has_all implementation

* Fixed failing flake8 check

* fix RandomPhotometricDistort

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

* add cleanup transformation for bounding boxes

* change the cleanup transform to an actual compose

* address review

* address naming

* use box_area op

* [skip ci] plural

* split compose into its parts and expose them

* cleanup

* more import cleanup

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

* use the same base class for Label and OneHotLabel

* mypy

* rename typevar

* Move imports on constructor.

* Turn `_F` to a property.

* fix linter

* Fix mypy

* Make it class-wide attribute.

* Add tests based on code review

* Making changes from code-reviews.

* Remove the new tests.

* Clean up.

* Adding comments.

* Update the comment link.

* add deprecated color conversion functionals

* allow grayscale tensor inputs in rgb_to_grayscale

* add cloning to tensor no-op

* improve todo comment

* [skip ci]

* use legacy kernels

use legacy kernels

* fix import

* remove duplicate code

* remove duplicate check

* Fix out-of-bounds read in decode_png

* Fix lint

* Use size_t instead of int to fix sign-compare check

* Add a unit-test to decode currupted png file

* Fix linter

* Update torchvision/csrc/io/image/cpu/decode_png.cpp

* Replace png_error with TORCH_CHECK
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Update error message

* Update error message
Co-authored-by: vfdev <vfdev.5@gmail.com>

* Fix linter
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: vfdev <vfdev.5@gmail.com>

* WIP

* [proto] Added SimpleCopyPaste transform

* Refactored and cleaned the implementation and added tests

* Fixing code

* Fixed code formatting issue

* Minor updates

* Fixed merge issue
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* cleanup prototype auto augment transforms

* remove custom fill parsing from auto augment

* fix MixUp and CutMix

* improve error message

* add dispatcher for erase image kernels

* simplify RandomErasing

* replace query_image with query_image_dimensions

* use value sentinel and fix test for RandomErasing

* image_dimensions -> chw

* remove BatchMultiCrop

* address review

* let FiveCrop return tuples

* WIP

* Fixed dtype correction and tests

* Removed PIL Image support and output always Tensor

* [proto] Fixed to_image_tensor and to_image_pil

* Fixed failing test

* S3D initial commit

* add model builder code and docstrings

* change classifier submodule, populate weights enum

* fix change of block args from List[List[int]] to ints

* add VideoClassification to transforms

* edit weights url for testing, add s3d to models.video init

* norm_layer changes

* norm_layer and args fix

* Overwrite default dropout

* Remove docs from internal submodules.

* Fix tests

* Adding documentation.

* Link doc from main models.rst

* Fix min_temporal_size

* Adding crop/resize parameters in references script

* Release weights.

* Refactor dropout.

* Adding the weights table in the doc
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Vasilis Vryniotis <vvryniotis@fb.com>

* port `FixedSizeCrop` from detection references to prototype transforms

* mypy

* [skip ci] call invalid boxes and corresponding masks and labels

* cherry-pick missing functions from #6401

* fix feature wrapping

* add test

* mypy

* add input type restrictions

* add test for _get_params

* fix input checks

* Added ETH3D stereo dataset

* Small doc-reformating

* Removed assertions with no use, changed np conversion

* Added ETH3D stereo dataset

* Removed assertions with no use, changed np conversion

* rebased on main

* Revert "Removed assertions with no use, changed np conversion"

This reverts commit 1478a8c056bbed59b6f4a67f78a5cfac84cc9fda.

* Update to np.bool instead of np.bool_

* lint and mypy nit fix

* test nit

* expand has_any and has_all to also accept check callables

* add test and fix has_all

* add support for simple tensor images to CutMix, MixUp and RandomIoUCrop

* remove TODO

* remove pythonic syntax sugar

* simplify

* use concreate examples in test rather than abstract ones

* simplify further