GitLab

* Adding code skeleton

* Adding MBConvConfig.

* Extend SqueezeExcitation to support custom min_value and activation.

* Implement MBConv.

* Replace stochastic_depth with operator.

* Adding the rest of the EfficientNet implementation

* Update torchvision/models/efficientnet.py

* Replacing 1st activation of SE with SiLU.

* Adding efficientnet_b3.

* Replace mobilenetv3 assets with custom.

* Switch to standard sigmoid and reconfiguring BN.

* Reconfiguration of efficientnet.

* Add repr

* Add weights.

* Update weights.

* Adding B5-B7 weights.

* Update docs and hubconf.

* Fix doc link.

* Fix typo on comment.

[FBcode->GH] Port quantize_val and dequantize_val into torchvision to avoid at::native and android xplat incompatibility (#4311)

Summary:
This diff ports `quantize_val` and `dequantize_val` from at::native to torchvision because native kernels are incompatible with android xplat builds (see D30234056).

This should only be temporary until we find a way to move those functions out of at::native, or until the at::native / android incompatibility disappears.

Reviewed By: fmassa

Differential Revision: D30393619

fbshipit-source-id: 18b7b1b349ad9a24088a120e23da7535f7fa7ddc
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* style: Added typing to models/video

* style: Fixed typing

* style: Fixed typing

* style: Fixed typing

* refactor: Removed default value for stem

* docs: Fixed docstring of VideoResNet

* style: Refactored typing

* docs: Fixed docstring

* style: Fixed typing

* docs: Specified docstring

* typing: Fixed tying

* docs: Fixed docstring

* Undoing change.

* style: Added typing annotations to segmentation/_utils

* style: Added typing annotations to segmentation/segmentation

* style: Added typing annotations to remaining segmentation models

* style: Fixed typing of DeepLab

* style: Fixed typing

* fix: Fixed typing annotations & default values

* Fixing python_type_check

* Adding operator.

* Adding tests

* switching order of `p` and `mode`.

* Remove seed setting.

* Replace stats import with pytest.importorskip.

* Fix doc

* Apply suggestions from code review
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Fixing indentation.

* Adding operator in the documentation.

* Fixing lint
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Unpinned the libjpeg version and fixed jpeg_mem_dest's size type Windows BC issue

* Temporarily get back pinned jpeg lib in order to run tests on CircleCI

* Revert "Temporarily get back pinned jpeg lib in order to run tests on CircleCI"

This reverts commit ab18a354150f750256b61911e54aa48621ef24cd.

* Used using instead of typedef and Fixed comment typo
Co-authored-by: Zhongkai Zhu <zhongkai@fb.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* fix

* add functional PIL typings

* fix types

* fix types

* fix a small one

* small fix

* fix type

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

* Replace in test_datasets*

* Replace in test_image.py

* Replace in test_transforms_tensor.py

* Replace in test_internet.py and test_io.py

* get_list_of_videos is util function still use get_tmp_dir

* Fix get_list_of_videos siginiture

* Add get_tmp_dir import

* Modify test_datasets_video_utils.py for test to pass

* Fix indentation

* Replace get_tmp_dir in util functions in test_dataset_sampler.py

* Replace get_tmp_dir in util functions in test_dataset_video_utils.py

* Move get_tmp_dir() to datasets_utils.py and refactor

* Fix pylint, indentation and imports

* import shutil to common_util.py

* Fix function signiture

* Remove get_list_of_videos under context manager

* Move get_list_of_videos to common_utils.py

* Move get_tmp_dir() back to common_utils.py

* Fix pylint and imports
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

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

* Skip the test if the failure is due to a connection error.

* Add todo.

* document video_sampler.

* minor docs for decoder.cpp

* descriptive comments for the stream.c

* descriptive comments for decoder.cpp

* per-stream descriptive comments

* Fixing CLANG hopefully

* addressing prabhat's comments

* typo I think
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* style: Added typing annotations

* style: Fixed typing

* style: Fixed typing

* Remove unnecessary any.

* Update mypy.ini
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Vasilis Vryniotis <vvryniotis@fb.com>

* style: Added missing typing annotations

* style: Fixed typing

* style: Fixed typing

* chore: Updated mypy.ini
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* interlaced png images
Co-authored-by: Vincent Moens <vmoens@fb.com>

Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Add CUDA-11.3 builds to torchvision

Also mark  `.cicrleci/config.yml` as autogenerated in `.gitattributes`

* Add CUDA-11.3 install steps for Windows

* And here as well

Co-authored-by: Vincent Moens <vmoens@fb.com>

* string manipulation for ffmpeg version retrieval

* ffmpeg version 4.2 control

* commenting solution

* removing all escapes for spaces
Co-authored-by: Vincent Moens <vmoens@fb.com>

using nn.init.trunc_normal_ instead of scipy.stats.truncnorm
Co-authored-by: Vincent Moens <vmoens@fb.com>

* WIP on backward op interpolation with AA

* Removed cuda tests and reformat cpp code

* Fixed clang wrong formatting

* Added channels last test case

* Added CUDA support for backward pass, interpolation with AA

* Removed unused buffers
Co-authored-by: vfdev-5 <vfdev-5@gmail.com>

* Port 'examples/python/video_api.ipynb' to gallery

* Address rst formattion suggestions

* test_video_reader pytest refactoring

* pytest refactoring of test_videoapi.py

* test_video_reader pytest refactoring

* pytest refactoring of test_videoapi.py

* using pytest.approx for test_video_reader.py

* using pytest.approx for test_videoapi.py

* Fixing minor comments

* linting fixes

* minor comments
Co-authored-by: Vincent Moens <vmoens@fb.com>

* fix MacOS cmake workflow

* try only mkl

* only pin mkl on MacOs

* fix
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* style: Added missing typing annotations

* style: Fixed last missing typing annotation

* chore: Fixed missing import

* style: Fixed typing

* refactor: Switched file selection from list to set
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Port test_datasets.py to use pytest

* A better replacement of self.assertSequenceEqual

* Migrate from equality check to identity check

* WIP on backward op interpolation with AA

* Removed cuda tests and reformat cpp code

* Fixed clang wrong formatting

* Added channels last test case
Co-authored-by: vfdev-5 <vfdev-5@gmail.com>
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

Signed-off-by: Edward Z. Yang <ezyang@fb.com>