GitLab

* mExplicitly copying array in pil_to_tensor

* Update torchvision/transforms/functional.py
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* Adding comments regarding implicit array deep copy in PILToTensor transform

* Update torchvision/transforms/transforms.py
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* add benchmark utility for datasets

* cleanup

* cleanup

* add benchmarks for MNIST and variants

* simplifiy return if exeception

* refactor benchmark instantiation logic
Co-authored-by: Prabhat Roy <prabhatroy@fb.com>

* Use FX feature extractor for segm model

* Removed use_fe option

Co-authored-by: Prabhat Roy <prabhatroy@fb.com>

Co-authored-by: Prabhat Roy <prabhatroy@fb.com>

Co-authored-by: Prabhat Roy <prabhatroy@fb.com>

* Updated classification reference script to use torch.cuda.amp

* Assigned scaler to None if amp is False

* Fixed linter errors

* add prototype datasets for MNIST and variants

* fix mypy

* fix EMNIST labels

* fix code format

* avoid encoding + decoding in every step

* discard data at the binary level instead of after decoding

* cleanup

* fix mypy

* Add docs for PILToTensor

* Update docs/source/transforms.rst
Co-authored-by: Aditya Oke <47158509+oke-aditya@users.noreply.github.com>
Co-authored-by: Aditya Oke <47158509+oke-aditya@users.noreply.github.com>

* add prototype dataset for CelebA

* fix code format

* fix mypy

* hardcode fmtparams

* fix mypy

* replace KeyZipper with Zipper for annotations

* add prototype for SBD dataset

* cleanup

* add prototype for VOC dataset

* fix code format

* fix mypy

* resolve todo

* Enhanced contributing guide

* Some more

* Address comments

* add prototype for CIFAR datasets

Conflicts:
	torchvision/prototype/datasets/_builtin/__init__.py
	torchvision/prototype/datasets/utils/_internal.py

* fix mypy

* cleanup

* more cleanup

* revert unrelated changes

* fix code format

* avoid decoding twice by default

* revert unrelated change

* cleanup

* Add str param

* Update test to include str

* Fix mypy

* Remove a small bracket

* Test more robustly

* Update docstring and test:

* Apply suggestions from code review
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* Update torchvision/utils.py

Small docstring fix

* Update torchvision/utils.py

* remove unnecessary renaming
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

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

* Allow redefinition for mypy

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

* add best weights and x_1_6, x_3_2, y_1_6, y_3_2, y_32 weights

* add best weights and x_1_6, x_3_2, y_1_6, y_3_2, y_32 weights

* add weights for x_16gf, x_32gf, y_16gf

* add ufmt as code formatter

* cleanup

* quote ufmt requirement

* split imports into more groups

* regenerate circleci config

* fix CI

* clarify local testing utils section

* use ufmt pre-commit hook

* split relative imports into local category

* Revert "split relative imports into local category"

This reverts commit f2e224cde2008c56c9347c1f69746d39065cdd51.

* pin black and usort dependencies

* fix local test utils detection

* fix ufmt rev

* add reference utils to local category

* fix usort config

* remove custom categories sorting

* Run pre-commit without fixing flake8

* got a double import in merge
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

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

* draft commit

* Polish and add corresponding test

* Update docs

* Update torchvision/models/feature_extraction.py

* Update docs/source/feature_extraction.rst
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Added PILToTensor and ConvertImageDtype classes in reference scripts

* Addressed review comments

* Fixed TypeError

* Addressed review comment

* add prototype for `Caltech256` dataset

* silence mypy

* add torchdata as prototype dependency

* ignore torchdata for mypy

* move git dependency out of conda environment file

* try unsetting PYTORCH_VERSION env var

* cleanup

* move installation of torchdata after installtion of PyTorch

* regenerate circlci config

* remove branch from torchdata download link
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Moving _make_divisible to utils.

* Replace the old ConvBNReLU and ConvBNActivation layers

* Fix minor bug.

* Moving SE layer to ops.

* Adding deprecation warnings on old layers.

* Apply changes to regnets.

* Change transforms gallery thumbnail

* Change visualization utils and repurposing annotations gallery thumbnails

* initial code

* add SqueezeExcitation

* initial code

* add SqueezeExcitation

* add SqueezeExcitation

* regnet blocks, stems and model definition

* nit

* add fc layer

* use Callable instead of Enum for block, stem and activation

* add regnet_x and regnet_y model build functions, add docs

* remove unused depth

* use BN/activation constructor and ConvBNActivation

* add expected test pkl files

* allow custom activation in SqueezeExcitation

* use ReLU as the default activation

* initial code

* add SqueezeExcitation

* initial code

* add SqueezeExcitation

* add SqueezeExcitation

* regnet blocks, stems and model definition

* nit

* add fc layer

* use Callable instead of Enum for block, stem and activation

* add regnet_x and regnet_y model build functions, add docs

* remove unused depth

* use BN/activation constructor and ConvBNActivation

* reuse SqueezeExcitation from efficientnet

* refactor RegNetParams into BlockParams

* use nn.init, replace np with torch

* update README

* construct model with stem, block, classifier instances

* Revert "construct model with stem, block, classifier instances"

This reverts commit 850f5f3ed01a2a9b36fcbf8405afd6e41d2e58ef.

* remove unused blocks

* support scaled model

* fuse into ConvBNActivation

* make reset_parameters private

* fix type errors

* fix for unit test

* add pretrained weights for 6 variant models, update docs

* Reuse EfficientNet SE layer.

* Deprecating the mobilenetv3.SqueezeExcitation layer.

* Passing the right activation on quantization.

* Making strict named param.

* Set default params if missing.

* Fixing typos.

* Add autouse fixture to save and reset RNG in tests

* Add other RNG generators

* delete freeze_rng_state

* Hopefully fix GaussianBlur test

* Alternative fix, probably better

* revert changes to test_models
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>