GitLab

* First PR for model doc revamp

* Deactivating fail on warning, temporarily

* Remove commnet

* Minor changes

* Typos

* Added TODO in Makefile

* Keep old models.rst file intact, move new docs into new models_new.rst file

* Add vit_b_16_swag

* Better handling idiom for image_size, edit test_extended_model to handle case where number of param differ from default due to different image size input

* Update the accuracy to the experiment result on torchvision model

* Fix typo missing underscore

* raise exception instead of torch._assert, add back publication year (accidentally deleted)

* Add license information on meta and readme

* Improve wording and fix typo for pretrained model license in readme

* Add vit_l_16 weight

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

* Update the accuracy meta on vit_l_16_swag model to result from our experiment

* Add vit_h_14_swag model

* Add accuracy from experiments

* Add to vit_h_16 model to hubconf.py

* Add docs and expected pkl file for test

* Remove legacy compatibility for ViT_H_14 model
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Test vit_h_14 with smaller image_size to speedup the test
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

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

* 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 documentation version problems

* add missing import

* linting

* Remove from models and references.

* Adding most tests and docs.

* Adding transforms tests.

* Remove unnecesary ipython notebook.

* Simplify tests.

* Addressing comments.

* Extend the EfficientNet class to support v1 and v2.

* Refactor config/builder methods and add prototype builders

* Refactoring weight info.

* Update dropouts based on TF config ref

* Update BN eps on TF base_config

* Use Conv2dNormActivation.

* Adding pre-trained weights for EfficientNetV2-s

* Add Medium and Large weights

* Update stats with single batch run.

* Add accuracies in the docs.

* Replace get_image_size/num_channels with get_image_dims

* Reduce verbosity

* Fix JIT-scriptability

* Refactoring

* More refactoring

* Replace all _FP/_FT direct calls.

* Remove usages of get_image_size and get_image_num_channels from code-base.

* Fix JIT issues

* Adding missing assertion.

* Create dropblock.py

* add dropblock2d

* fix pylint

* refactor dropblock

* add dropblock

* Rename dropblock.py to drop_block.py

* fix pylint

* add dropblock

* add dropblock3d

* add drop_block3d

* add dropblock

* Update drop_block.py

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

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

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

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

* Update drop_block.py

* Update drop_block.py

* import torch.fx

* fix lint

* fix lint

* Update drop_block.py

* improve dropblock

* add dropblock

* refactor dropblock

* fix doc

* remove the limitation of block_size

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

* fix lint

* fix lint

* add dropblock

* Fix linter

* add dropblock random check

* reduce test time

* Update test_ops.py

* speed the dropblock test

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

* Add ops.conv3d

* Refactor for conv2d and 3d

* Refactor

* Fix bug

* Addres review

* Fix bug

* nit fix

* Fix flake

* Final fix

* remove documentation

* fix linter

* Update all the implementations to use new Conv

* Small doc fix
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Joao Gomes <jdsgomes@fb.com>

* Adding basic augmix implementation.

* Finish the implementation.

* Add tests and documentation.

* Fix tests.

* Simplify code.

* Speed optimizations.

* Per image weights instead of per batch.

* Fix tests.

* Update torchvision/transforms/autoaugment.py
Co-authored-by: vfdev <vfdev.5@gmail.com>

* Changing the default severity value to get by default the same strength as RandAugment.
Co-authored-by: vfdev <vfdev.5@gmail.com>

* properly deprecate legacy implementation

* cleanup

* use warning over deprecation directive

* remove patch version

* fix link in Kinetics docstring

* Some more

* fix affine functional tests
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* Remove APIs that were deprecated before 0.8

* More stuff

* Some more

* oops

* Improve giou loss

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

* Graduate ConvNeXt to main TorchVision area.

* Linter and all var.

* Renaming var and making named params mandatory.

* Refactor model builder

* Add 3 more convnext variants.

* Adding weights for convnext_small.

* Fix minor bug.

* Fix number of parameters for small model.

* Adding weights for the base variant.

* Adding weights for the large variant.

* Simplify LayerNorm2d implementation.

* Optimize speed of CNBlock.

* Repackage weights.

* Start stuff

* Start adding some implementation

* Add implementation

* Use torch for colorwheel

* Add simple test

* Fix small numpy rename

* Adapt the changes

* Fix stuff

* Add suggestions

* Minor fixes for float

* Remove idx logic

* Simplify

* Fix test

* Update code and add test

* Add expected flow asset

* Fix expected flow path

* Doc nits
Co-authored-by: Nicolas Hug <nicolashug@fb.com>
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* add fcos

* update fcos

* add giou_loss

* add BoxLinearCoder for FCOS

* add full code for FCOS

* add giou loss

* add fcos

* add __all__

* Fixing lint

* Fixing lint in giou_loss.py

* Add typing annotation to fcos

* Add trained checkpoints

* Use partial to replace lambda

* Minor fixes to docstrings

* Apply ufmt format

* Fixing docstrings

* Fixing jit scripting

* Minor fixes to docstrings

* Fixing jit scripting

* Ignore mypy in fcos

* Fixing trained checkpoints

* Fixing unit-test of jit script

* Fixing docstrings

* Add test/expect/ModelTester.test_fcos_resnet50_fpn_expect.pkl

* Fixing test_detection_model_trainable_backbone_layers

* Update test_fcos_resnet50_fpn_expect.pkl

* rename stride to box size

* remove TODO and fix some typo

* merge some code for better

* impove the comments

* remove decode and encode of BoxLinearCoder

* remove some unnecessary hints

* use the default value in detectron2.

* update doc

* Add unittest for BoxLinearCoder

* Add types in FCOS

* Add docstring for BoxLinearCoder

* Minor fix for the docstring

* update doc

* Update fcos_resnet50_fpn_coco pretained weights url

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

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

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

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

* Add FCOS model documentation

* Fix typo in FCOS documentation

* Add fcos to the prototype builder

* Capitalize COCO_V1

* Fix params of fcos

* fix bug for partial

* Fixing docs indentation

* Fixing docs format in giou_loss

* Adopt Reference for GIoU Loss

* Rename giou_loss to generalized_box_iou_loss

* remove overwrite_eps

* Update AP test values

* Minor fixes for the docs

* Minor fixes for the docs

* Update torchvision/models/detection/fcos.py
Co-authored-by: Zhiqiang Wang <zhiqwang@foxmail.com>

* Update torchvision/prototype/models/detection/fcos.py
Co-authored-by: Zhiqiang Wang <zhiqwang@foxmail.com>
Co-authored-by: zhiqiang <zhiqwang@foxmail.com>
Co-authored-by: Joao Gomes <jdsgomes@fb.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Joao Gomes <joaopsgomes@gmail.com>

* Adding CNBlock and skeleton architecture

* Completed implementation.

* Adding model in prototypes.

* Add test and minor refactor for JIT.

* Fix mypy.

* Fixing naming conventions.

* Fixing tests.

* Fix stochastic depth percentages.

* Adding stochastic depth to tiny variant.

* Minor refactoring and adding comments.

* Adding weights.

* Update default weights.

* Fix transforms issue

* Move convnext to prototype.

* linter fix

* fix docs

* Addressing code review comments.

* Adding multiweight support for shufflenetv2 prototype models

* Revert "Adding multiweight support for shufflenetv2 prototype models"

This reverts commit 31fadbee7d1a65cd73ae43dfd4ac6e97e7ca7b01.

* Adding multiweight support for shufflenetv2 prototype models

* Revert "Adding multiweight support for shufflenetv2 prototype models"

This reverts commit 4e3d900f796c1e3e667312087e77956ca4a4c017.

* Add RenderedSST2 dataset

* Address PR comments

* Fix bug in dataset verification
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* adding vit_h_14

* prototype and docs

* bug fix

* adding curl check

* [WIP]
*added stanford_cars

* [WIP]
added stanfordCars to docs

* [WIP]
minor edits

* [WIP]
minor edits

* edited StanfordCars class

* Adding Testcase for stanford cars

* Added Testcase for stanford cars

* Added Testcase for stanford cars

* minor edit

* made changes as per the suggestions

* fixed typo in naming stanford_cars.py

* cars_meta.mat file will be created in test

* Some cleanups

* Sigh

* don't convert to strings
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* feat: Added EuroSAT dataset

* test: Added unittest

* docs: Improved comments

* docs: Updated the documentation

* docs: Removed unnecessary comments

* fix: Fixed class implementation

* test: Fixed unittest

* fix: Fixed magic method len

* test: Fixed unittest

* refactor: Refactored EuroSAT

* refactor: Applied modifications

* Apply suggestions from code review

* refactor: Applied request changes

* refactor: Made var explicit

* fix: Fixed attribute initialization order

* refactor: Removed name mapping
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Add support for PCAM dataset

* mypy

* Apply suggestions from code review
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Remove classes and class_to_idx attributes

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

* add fvgc_aircraft dataset

* add docstring & remove useless import

* resolve lint issue

* address comments

* adding more annotation level

* nit

* address comments

* Apply suggestions from code review

* unify format

* remove useless line
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* add regnet_y_128gf

* fix test

* add expected test file

* update regnet factory function, add to prototype as well

* write torchscript to temp file instead bytesio in model test

* docs

* clear GPU memory

* no_grad

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

* Add Flowers102 datasets

* Fix initialization of images and labels

* Fix _check_exists in Flowers102

* Add Flowers102 to datasets and docs

* Add Flowers102TestCase to unittest

* Fixing Python type statically

* Shuffle the fake labels

* Update test/test_datasets.py
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Apply the suggestions by pmeier

* Use check_integrity to check file existence

* Save the labels to base_folder

* Minor fixes

* Using a loop makes this more concise without reducing readability
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Using a loop makes this more concise without reducing readability
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Remove self.labels and self.label_to_index attributes

* minor simplification

* Check the exitence of image folder

* Revert the check

* Check the existence of image folder

* valid -> val

* keep some stuff private

* minor doc arrangements

* remove default FEATURE_TYPES

* Simplify the datasets existence

* check if the image folder exists
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* isdir -> is_dir
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* graduate vit from prototype

* nit

* add vit to docs and hubconf

* ufmt

* re-correct ufmt

* again

* fix linter

* Add Country211 dataset

To addresses issue #5108.

* Add Country211 dataset

To addresses issue #5108.

* Update country211.py

* Update country211.py

* Code review reflected

Reflect code review

* Update test_datasets.py

* Update with review

Update with review

* inherit from ImageFolder

* Update test/test_datasets.py

* Docstring + minor test update
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* dataset class added

* fix code format

* fixed requested changes

* fixed issues in sun397

* Update torchvision/datasets/sun397.py
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* add prototype dataset for oxford-iiit-pet

* add old-style dataset

* add tests

* fix mypy

* fix test

* remove properties and use pathlib

* target_type to target_types

* move target annotation

* add docstring

* fix test

* Added GTSRB dataset

* Added unittest for GTSRB dataset

* Apply suggestions from code review

* More changes from code review

* readd accidental removed line
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* add prototype dataset

* add old style dataset

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

* refactor integrity check
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* add DTD as prototype dataset

* add old style dataset

* add test for old dataset

* fix tests for windows

* add dataset to docs

* remove properties and use pathlib

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

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

* Adding multiweight support for shufflenetv2 prototype models

* Revert "Adding multiweight support for shufflenetv2 prototype models"

This reverts commit 31fadbee7d1a65cd73ae43dfd4ac6e97e7ca7b01.

* Adding multiweight support for shufflenetv2 prototype models

* Revert "Adding multiweight support for shufflenetv2 prototype models"

This reverts commit 4e3d900f796c1e3e667312087e77956ca4a4c017.

* Add Food101 Dataset

Addresses #5108.
cc @pmeier @NicolasHug

* Remove unecessary Path contructor calls

* Remove unecessary Path contructor callsi and fix types

* Fix tests

* Address PR comments from @pmeier

* Fix bug in tests and in food101 dataset

* Fix bug in tests and in food101 dataset

* Update torchvision/datasets/food101.py
Co-authored-by: Philip Meier <github.pmeier@posteo.de>