GitLab

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

* intial structure

* fixed types of few variables

* remove the commented code

* list -> List

* encode method will take input as tensors instead of list of tensor
Co-authored-by: Joao Gomes <jdsgomes@fb.com>

* Update git-blame-ignore-revs following new ufmt version

* Un-do ufmt version changed, got mixed up

* upgrade usort to

* Also update black

* Actually use 1.0.2

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

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

Co-authored-by: Alexander Jipa <azzhipa@amazon.com>

* fix inplace mutation

* Different attn shouldn't share the same attribute

* a simpler solution
Co-authored-by: YosuaMichael <yosuamichaelm@gmail.com>

* Moved pfm file reading into dataset utils

* Made _read_pfm private. Fixed doc format issues.

* 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

* Make ConvNormActivation function accept tuple for kernel_size, stride, padding, and dilation

* Fix the method to get the conv_dim

* Simplify if-elif logic

* Updated tests to save and load transforms

* Fixed code formatting issue

* Add ensembled video accuracy on video reference script

* Change the parser func to be similar with classification reference

* Fix typo type->dtype

* Use custom kinetics

* Fix dataset to not getting start_pts

* Change dataset name, and put video_idx at the back

* Ufmt format

* Use functional softmax, updating meta and use it to overwrite eval param

* Fix typo

* Put the eval parameters on the docs for now

* Change meta for video resnet to use frame-rate 15, also change wording on docs

* Added mid-level ops and feature-based ops

* Fixing deadlock in dataloader with circular imports

* Added non-scalar fill support workaround for pad

* Removed comments

* int/float support for fill in pad op

* Updated type hints and removed bypass option from mid-level methods

* Minor nit fixes

* basic structure

* added constrains

* fixed errors

* thanks to vadim!

* addressing the comments and added docstrign

* Apply suggestions from code review
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Make `_log_api_usage_once` work for overwritten classes

* Change module prefix to `torchvision.internal`

* Refactor setup.py to build only wanted extensions.

* Improve visual feedback for libpng support in setup.py.

* Improve printing of extensions finding in setup.py.

* Fix linter errors.

* Apply suggestions from code review
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Update the dataset cache to factor in parameters from the args.

* Fix linter

To make project https://peps.python.org/pep-0517/ compliant

Solves https://github.com/pytorch/pytorch/issues/80745

* Adding MViT v2 architecture (#6105)

* Adding mvitv2 architecture

* Fixing memory issues on tests and minor refactorings.

* Adding input validation

* Adding docs and minor refactoring

* Add `min_temporal_size` in the supported meta-data.

* Switch Tuple[int, int, int] with List[int] to support easier the 2D case

* Adding more docs and references

* Change naming conventions of classes to follow the same pattern as MobileNetV3

* Fix test breakage.

* Update todos

* Performance optimizations.

* Add support to MViT v1 (#6179)

* Switch implementation to v1 variant.

* Fix docs

* Adding back a v2 pseudovariant

* Changing the way the network are configured.

* Temporarily removing v2

* Adding weights.

* Expand _squeeze/_unsqueeze to support arbitrary dims.

* Update references script.

* Fix tests.

* Fixing frames and preprocessing.

* Fix std/mean values in transforms.

* Add permanent Dropout and update the weights.

* Update accuracies.

* Fix documentation

* Remove unnecessary expected file.

* Skip big model test

* Rewrite the configuration logic to reduce LOC.

* Fix mypy

* Add flag to ignore ffmpeg in python build.

* Update setup.py to avoid potential collisions with other projects that are using FFMPEG
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* Added base tests for rotate_image_tensor

* Updated resize_image_tensor API and tests and fixed a bug with max_size

* Refactored and modified private api for resize functional op

* Fixed failures

* More updates

* Updated proto functional op: resize_image_*

* Added max_size arg to resize_bounding_box and updated basic tests

* Update functional.py

* Reverted fill/center order for rotate
Other nits

* Refactored and modified private api for resize functional op

* Fixed failures

* More updates

* Fixed flake8

* Add rough raft-stereo implementation on prototype/models

* Add standard raft_stereo builder, and modify context_encoder to be more similar with original implementation

* Follow original implementation on pre-convolve context

* Fix to make sure we can load original implementation weight and got same output

* reusing component from raft

* Make the raft_stereo_fast able to load original weight implementation

* Format with ufmt and update some comment

* Use raft FlowHead

* clean up comments

* Remove unnecessary import and use ufmt format

* Add __all__ and more docs for RaftStereo class

* Only accept param and not module for raft stereo builder

* Cleanup comment

* Adding typing to raft_stereo

* Update some of raft code and reuse on raft stereo

* Use bool instead of int

* Make standard raft_stereo model jit scriptable

* Make the function _make_out_layer using boolean with_block and init the block_layer with identity

* Separate corr_block into two modules for pyramid and building corr features

* Use tuple if input is not variable size, also remove default value if using List

* Format using ufmt and update ConvGRU to not inherit from raft in order to satisfy both jit script and mypy

* Change RaftStereo docs input type

* Ufmt format raft

* revert back convgru to see mypy errors, add test for jit and fx, make the model fx compatible

* ufmt format

* Specify device for new tensor, dont init module then overwrite and put if-else instead

* Ignore mypy problem on override, put back num_iters on forward

* Revert some effort to make it fx compatible but unnecessary now

* refactor code and remove num_iters from RaftStereo constructor

* Change to raft_stereo_realtime, and specify device directly for tensor creation

* Add description for raft_stereo_realtime

* Update the test for raft_stereo

* Fix raft stereo prototype test to properly test jit script

* Ufmt format

* Test against expected file, change name from raft_stereo to raft_stereo_builder to prevent import error

* Revert __init__.py changes

* Add default value for non-list param on model builder

* Add checking on out_with_block length, add more docs on the encoder

* Use base instead of basic since it is more commonly used

* rename expect file to base as well

* rename on test

* Revert the revert of __init__.py, also revert the adding default value to _raft_stereo to follow the standard pattern

* ufmt format __init__.py

Summary:
fixes two sporadic issues from missing attributes:

- breaking circular imports
- submodule not being imported explicitly

Reviewed By: ehhuang

Differential Revision: D37071652

fbshipit-source-id: 0680f098384b0fd21076339750e9d1a96186ede3
Co-authored-by: Edward Wang (EcoF) <hack@fb.com>