GitLab

Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: vfdev-5 <vfdev.5@gmail.com>

* rename features._Feature to datapoints.Datapoint

* _Datapoint to Datapoint

* move is_simple_tensor to transforms.utils

* fix CI

* move Datapoint out of public namespace

* expose some prototype transforms utils

* rename _isinstance

* fix prototype kernels

* fix stable kernels

* fix tests

* make test more robust

* improve invert for signed integers

* improve invert

* fix posterize

* Revert "assume that integer images are [0, 255] in equalize (#6859)"

This reverts commit 436ff9a5

.

* fix solarize in AA

* fix resize

* Revert "fix resize"

This reverts commit 5f33f4aa73e098237650b794157ec9335d964152.

* add comment to float max value
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Adjust solarize threshold on input type

* Handle PIL images

* minor refactor

* Fix linter

* 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

* Removing unnecessary methods/classes.

* Unions instead of ImageOrVideo types

* Fixing JIT issue.

* 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

* 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

* Align and Clean up transform types

* Move type definitions to `_utils.py`

* fixing error message on tests

* Apply code review suggestions
Co-authored-by: vfdev <vfdev.5@gmail.com>

* Centralizing types and switching to always getting dicts.

* Fixing linter

* Refactoring typing definitions.

* Remove relative imports.

* Reuse type.

* Temporarily remove the TorchData tests.

* Restore the TorchData tests.
Co-authored-by: vfdev <vfdev.5@gmail.com>

* [proto] Fixed fill type in AA

* Fixed missed typehints

* Set fill as None by default

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

* Improve existing low kernel test.

* Add new midlevel jit-scriptability test (failing).

* Remove duplicate aliases from kernel tests.

* Fixing colour kernels.

* Fixing deprecated kernels.

* fix mypy

* Silence mypy instead of fixing to avoid performance penalty

* Fixing augment kernels.

* Fixing augment meta.

* Remove is_tracing calls.

* Add fake ImageType and DType

* Fixing type conversion kernels.

* Fixing misc kernels.

* partial fix geometry

* Remove mutable default from `_pad_with_vector_fill()` + all other unnecessary defaults.

* Fix geometry ops

* Fixing tests

* Removed xfail for jit tests on midlevel ops
Co-authored-by: vfdev-5 <vfdev.5@gmail.com>

* Remove alias for `pil_to_tensor()`

* Remove alias for `PILToTensor`

* Leave `to_tensor()` as-is.

* Fix linter

* rename features.SegmentationMask -> features.Mask

* rename kernels *_segmentation_mask -> *_mask and cleanup input name

* cleanup

* rename module _segmentation_mask.py -> _mask.py

* fix test

* check signatures of all available transformations

* fix signatures of RandAugment and TrivialAugmentWide

* move AA consistency tests to correct module

* clean up bboxes

* Correcting bug on RandAugment.

* Fix bug on erase()

* Moving `_parse_pad_padding()` to functional geometry

* Fixing bug on deprecated Grayscale transforms

* Porting old bugfixes from main branch to _apply_image_transform

* Dropping mandatory keyword arguments to maintain BC.

* Adding antialias option where possible.

* Specifying types in `_transform()` where possible.

* Add todo.

* Fixing tests.

* Adding padding_mode in pad_bbox
Co-authored-by: vfdev <vfdev.5@gmail.com>

* [proto] Fixed RandAug implementation

* Fixed randomness in tests for trivial aug

* Fixed all AA tests

* 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

* 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>

* cleanup prototype auto augment transforms

* remove custom fill parsing from auto augment

* 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

* replace query_recursively with pytree implementation

* simplify
Co-authored-by: vfdev <vfdev.5@gmail.com>

* upgrade usort to

* Also update black

* Actually use 1.0.2

* Apply pre-commit
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* Another attempt to add transforms

* Fixed padding type hint

* Fixed fill arg for pad and rotate, affine

* code formatting and type hints for affine transformation

* Fixed flake8

* Updated tests to save and load transforms

* Fixed code formatting issue

* Fixed jit loading issue

* Restored fill default value to None
Updated code according to the review

* Added tests for rotation, affine and zoom transforms

* Put back commented code

* Random erase bypass boxes and masks
Go back with if-return/elif-return/else-return

* Fixed acceptable and non-acceptable types for Cutmix/Mixup

* Updated conditions for _BaseMixupCutmix

* Moving basefiles outside of prototype and porting Alexnet, ConvNext, Densenet and EfficientNet.

* Porting googlenet

* Porting inception

* Porting mnasnet

* Porting mobilenetv2

* Porting mobilenetv3

* Porting regnet

* Porting resnet

* Porting shufflenetv2

* Porting squeezenet

* Porting vgg

* Porting vit

* Fix docstrings

* Fixing imports

* Adding missing import

* Fix mobilenet imports

* Fix tests

* Fix prototype tests

* Exclude get_weight from models on test

* Fix init files

* Porting googlenet

* Porting inception

* porting mobilenetv2

* porting mobilenetv3

* porting resnet

* porting shufflenetv2

* Fix test and linter

* Fixing docs.

* Porting Detection models (#5617)

* fix inits

* fix docs

* Port faster_rcnn

* Port fcos

* Port keypoint_rcnn

* Port mask_rcnn

* Port retinanet

* Port ssd

* Port ssdlite

* Fix linter

* Fixing tests

* Fixing tests

* Fixing vgg test

* Porting Optical Flow, Segmentation, Video models (#5619)

* Porting raft

* Porting video resnet

* Porting deeplabv3

* Porting fcn and lraspp

* Fixing the tests and linter

* Porting docs, examples, tutorials and galleries (#5620)

* Fix examples, tutorials and gallery

* Update gallery/plot_optical_flow.py
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* Fix import

* Revert hardcoded normalization

* fix uncommitted changes

* Fix bug

* Fix more bugs

* Making resize optional for segmentation

* Fixing preset

* Fix mypy

* Fixing documentation strings

* Fix flake8

* minor refactoring
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* Resolve conflict

* Porting model tests (#5622)

* Porting tests

* Remove unnecessary variable

* Fix linter

* Move prototype to extended tests

* Fix download models job

* Update CI on Multiweight branch to use the new weight download approach (#5628)

* port Pad to prototype transforms (#5621)

* port Pad to prototype transforms

* use literal

* Bump up LibTorchvision version number for Podspec to release Cocoapods (#5624)
Co-authored-by: Anton Thomma <anton@pri.co.nz>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* pre-download model weights in CI docs build (#5625)

* pre-download model weights in CI docs build

* move changes into template

* change docs image

* Regenerated config.yml
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Anton Thomma <11010310+thommaa@users.noreply.github.com>
Co-authored-by: Anton Thomma <anton@pri.co.nz>

* Porting reference scripts and updating presets (#5629)

* Making _preset.py classes

* Remove support of targets on presets.

* Rewriting the video preset

* Adding tests to check that the bundled transforms are JIT scriptable

* Rename all presets from *Eval to *Inference

* Minor refactoring

* Remove --prototype and --pretrained from reference scripts

* remove  pretained_backbone refs

* Corrections and simplifications

* Fixing bug

* Fixing linter

* Fix flake8

* restore documentation example

* minor fixes

* fix optical flow missing param

* Fixing commands

* Adding weights_backbone support in detection and segmentation

* Updating the commands for InceptionV3

* Setting `weights_backbone` to its fully BC value (#5653)

* Replace default `weights_backbone=None` with its BC values.

* Fixing tests

* Fix linter

* Update docs.

* Update preprocessing on reference scripts.

* Change qat/ptq to their full values.

* Refactoring preprocessing

* Fix video preset

* No initialization on VGG if pretrained

* Fix warning messages for backbone utils.

* Adding star to all preset constructors.

* Fix mypy.
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Anton Thomma <11010310+thommaa@users.noreply.github.com>
Co-authored-by: Anton Thomma <anton@pri.co.nz>

* fix vanilla tensor image detection

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

* fix grayscale to RGB for batches

* make unsupported types in auto augment a parameter

* make auto augment kwargs explicit

* add missing error message

* add support for specifying probabilites on RandomChoice

* remove TODO for deprecating p on random transforms

* streamline sample type checking

* address comments

* split image_size into height and width in auto augment
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* add prototype AugMix transform

* cleanup

* refactor auto augment subclasses to only trnasform a single image

* address review comments