GitLab

* 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>

* Added maxvit architecture and tests

* rebased + addresed comments

* Revert "rebased + addresed comments"

This reverts commit c5b28398cd48d2f3403c7c8eeefbaba9df05fcfe.

* Re-added model changes after revert

* aligned with partial original implementation

* removed submitit script fixed lint

* mypy fix for too many arguments

* updated old tests

* removed per batch lr scheduler and seed setting

* removed ontap

* added docs, validated weights

* fixed test expect, moved shape assertions in the begging for torch.fx compatibility

* mypy fix

* lint fix

* added legacy interface

* added weight link

* updated docs

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

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

* adressed comments

* update ra_maginuted and augmix_severity default values

* adressed some comments

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

* add coverage to prototype tests CI

* line continuation

* add KernelInfo for adjust_brightness

* add KernelInfo for adjust_contrast

* add KernelInfo for adjust_hue

* add KernelInfo for adjust_saturation

* add KernelInfo for clamp_bounding_box

* add KernelInfo for {five, ten}_crop_image_tensor as well as skip functionality

* add KernelInfo for normalize

* add KernelInfo for adjust_gamma

* cleanup

* add DispatcherInfo's for previously add KernelInfo's

* add dispatcher info for elastic

* cleanup prototype transforms functional tests

* fix

* oust local functions

* [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>

* Added transforms for Stereo Matching

* changed implicit Y scaling to 0.

* Adressed some comments

* addressed type hint

* Added interpolation random interpolation strategy

* Aligned crop get params

* fixed bug in RandomErase

* Adressed scaling and typos

* Adressed occlusion typo

* Changed parameter order in F.erase

* fixed random erase

* Added inference preset transform for stereo matching

* added contiguous reshape to output tensors

* Adressed comments

* Modified the transform preset to use Tuple[int, int]

* adressed NITs

* added grayscale transform, align resize -> mask

* changed max disparity default behaviour

* added fixed resize, changed masking in sparse flow masking

* update to align with argparse

* changed default mask in asymetric pairs

* moved grayscale order

* changed grayscale api to accept to tensor variant

* mypy fix

* changed resize specs

* adressed nits

* added type hints

* mypy fix

* mypy fix

* mypy fix
Co-authored-by: Joao Gomes <jdsgomes@fb.com>

* Moved more losses into classes

* Added photometric loss

* quick fix for ssim loss return value

* added references

* replaced with unsqueeze

* renaming variables

* add ref to consistency loss

* made mask optional everywhere. generalised photometric displacement

* smoothness typo

* fixed flow channel selection bug

* aligned with training script
Co-authored-by: Joao Gomes <jdsgomes@fb.com>

* port vertical_flip

* port rotate

* port crop

* port resized_crop

* port pad

* port perspective

* port elastic

* port center_crop

* port gaussian_blur

* port equalize

* port invert

* port posterize

* port solarize

* port autocontrast

* port adjust_sharpness

* port erase

* fix kernel infos

* renable crop references

* add tolerances to gaussian_blur kernel info

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

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

Co-authored-by: Nicolas Hug <contact@nicolas-hug.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>

* ADD: init_weights config for googlenet

* Fix: Inception and googlenet warnings

* Fix: warning in test_datasets.py

* Fix: Formatting error with ufmt

* Fix: Failing tests in quantized_classification_model

* Update test/test_models.py to make googlenet in 1 line
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Refactor: Change inception quantisation class initialization to use args/kwargs

* Resolve mypy issue

* Move *args before inception_blocks

* Move args keywords before other arguments
Co-authored-by: Ambuj Pawar <your_email@abc.example>
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* add xfailed smoke tests for dispatchers

* also support old FunctionalInfo's

* try reduce memory consumption for CI

* fix sample inputs generation
Co-authored-by: vfdev <vfdev.5@gmail.com>

* Updated fill arg typehint for affine, perspective and elastic ops

* Updated pad op on prototype side

* Code updates

* Few other minor updates

* WIP

* WIP

* Updates

* Update _image.py

* Fixed tests

* Updated fill arg typehint for affine, perspective and elastic ops

* Updated pad op on prototype side

* Code updates

* Few other minor updates

- call torch.log once can save few ms
- all masks should be selected with is_within_crop_area in RandomIoUCrop
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

Not sure what have changed between CUDA-11.3 and CUDA-11.6, but bumping tolerance keeps tests green

* fix convert_format_bounding_box, affine_bounding_box, and resize_bounding_box

* fix perspective and elastic

* fix tests

* fix PIL and tensor mask comparison

* introduce kernel_name field

* add dtype consistency test

* port some tests from old framework

* add kernel infos for conversion kernels

* cleanup

* use nearest and bicubic for resize image sample inputs

* make parametrization id more obvious

* use named sentinel instead of None for random image size

* Remove alias for `pil_to_tensor()`

* Remove alias for `PILToTensor`

* Leave `to_tensor()` as-is.

* Fix linter

* crestereo draft implementation

* minor model fixes. positional embedding changes.

* aligned base configuration with paper

* Adressing comments

* Broke down Adaptive Correlation Layer. Adressed some other commets.

* adressed some nits

* changed search size, added output channels to model attrs

* changed weights naming

* changed from iterations to num_iters

* removed _make_coords, adressed comments

* fixed jit test

* config nit

* Changed device arg to str
Co-authored-by: Joao Gomes <jdsgomes@fb.com>
Co-authored-by: YosuaMichael <yosuamichaelm@gmail.com>

* [proto] Added consistency tests for detection transforms

* Updated tests according to the review

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

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

* reduce verbosity of prototype tests and split them into multiple steps

* rename builtin datasets module to fit common scheme

* Rename `convert_bounding_box_format` => `convert_format_bounding_box`

* Add missed replacement.

* Fix bug on `get_image_size()` and move it to deprecated. Introduce generic named spatial/channel equivalents.

* Update tests and fix mypy issues.

* Remove the use of get_image_size from ElasticTransform.

* Fix linter

* Apply suggestions from code review.

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

* Further changes from code review.

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

Fix cuda 11.6 and 11.7

Check nvjpeg from CONDA Path

More cuda11.6

Trying to fix the build

Trying to fix the build

Removing nvjpeg logic

Add NvToolsExt dll path

Fix lint