GitLab

* fix typos throughout the code base

* fix grammar

* revert formatting changes to gallery

* revert 'an uXX'

* remove 'number of the best'

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

* Add ValueError

* Add tests for ValueError

* Add tests for ValueError

* Add ValueError

* Change to if/else

* Ammend iou_fn tests

* Move code excerpt

* Format tests
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Rephrase ONNX RoiAlign warning for aligned=True

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

* Support exporting RoiAlign align=True to ONNX with opset 16

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

* Remove Kinetics400 class

* Remove '2007-test' in VOC

* Remove some MobileNet layer classes

* Remove torchvision/models/segmentation/segmentation.py

* Remove some MultiScaleRoIAlign methods

* Remove torchvision/transforms/_functional_video.py

* Remove torchvision/transforms/_transforms_video.py

* Remove resample parameter in transforms

* Remove 'range' parameter

* Remove 'fill_value' parameter in transforms

* Revert to original warning for C++ models - looks like we should still keep them around?

* pre-commit

* Fix docs

* Remove test/test_transforms_video.py

* Some fixes

* Remove more tests

* Revert changes to C++ models

* Add back _transforms_video and change warning message

* Change back the warning message, and will change the warning message on separate PR
Co-authored-by: YosuaMichael <yosuamichaelm@gmail.com>
Co-authored-by: Yosua Michael Maranatha <yosuamichael@fb.com>

* update roipool to make in torch fx traceable

* update ps_roi_align, ps_roi_pool and roi_align to make them torch fx traceable

* add unittest

* Remove `.to(output_fx)` from test
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Fix typing jit issue on RoIPool and RoIAlign

* Fix nit.

* Address code review comments.

* Fix bug in calculating cIoU for unequal sizes

* Remove comment

* what the epsilon?

* Fixing DIoU

* Optimization by Francisco.

* Fix the expected values on CompleteBoxIoU

* Apply suggestions from code review
Co-authored-by: Abhijit Deo <72816663+abhi-glitchhg@users.noreply.github.com>

* Adding cartesian product test.

* remove static
Co-authored-by: Vasilis Vryniotis <vvryniotis@fb.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Abhijit Deo <72816663+abhi-glitchhg@users.noreply.github.com>

* upgrade usort to

* Also update black

* Actually use 1.0.2

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

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

* Fix the method to get the conv_dim

* Simplify if-elif logic

* Adding an MLP block.

* Adding documentation

* Update typos.

* Fix inplace for Dropout.

* Apply recommendations from code review.

* Making changes on pre-trained models.

* Fix linter

* Cleanup ops

* Address nits
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* [FEAT] Add distance IoU and distance IoU loss + some tests (WIP for tests).

* [FIX] Remove URL from docstring + remove assert since it causes a big performance drop.

* [FIX] eps isn't None.

* [TEST] Update existing box dIoU test + add dIoU loss tests (inspired from cIoU ones).

* [ENH] Some pre-commit fixes + remove print + mypy.

* [ENH] Pass the device in the assertion for the dIoU loss test.

* [FIX] Remove type hints from the dIoU box test.

* [ENH] Refactor box and loss for dIoU functions + fix half tests.

* [FIX] Precommits fix.

* [ENH] Some improvement for the distance IoU tests thanks to code review.

* [ENH] Upcast in distance boxes computation to avoid overflow.

* [ENH] Revert the refactor of distance IoU loss back since it introduced a bug and can be slow.

* Precommit fix.

* [FIX] Few changes introduced by merge conflict.

* Add code reference

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

* added ciou loss

* "formatting with flake8 and ufmt"

* formatting with ufmt and flake8

* minor changes

* changes as per the suggestions

* added reference in torchvision/ops/__init__.py

* sample test

* tests formatted

* added description

* formatting

* edited tests

* changes in tests

* added tests for multiple boxes

* minor edits

* minor edit

* doc added

* minor edits

* Update test_ops.py

* formatting test file

* changes as per the suggestions

* formatting and adding some more tests

* bounding box added

* removed unnecessary comment

* added docstring

* added type annotations

* removed potential bug

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

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

* Update test/test_ops.py
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Convert weights only if `old_key` is in `state_dict`

* Fix linter

* Update focal_loss.py

updated docstring for the `sigmoid_focal_loss`

* edited docstring of focal_loss

* Update focal_loss.py

* fix doc style.

* formatting

* formatting

* minor edits

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

* Update _register_onnx_ops.py

* Update misc.py

* Use frozen BN only if pre-trained.

* Add LSJ and ability to from scratch training.

* Fixing formatter

* Adding `--opt` and `--norm-weight-decay` support in Detection.

* Fix error message

* Make ScaleJitter proportional.

* Adding more norm layers in split_normalization_params.

* Add FixedSizeCrop

* Temporary fix for fill values on PIL

* Fix the bug on fill.

* Add RandomShortestSize.

* Skip resize when an augmentation method is used.

* multiscale in [480, 800]

* Add missing star

* Add new RetinaNet variant.

* Add tests.

* Update expected file for old retina

* Fixing tests

* Add FrozenBN to retinav2

* Fix network initialization issues

* Adding BN support in MaskRCNNHeads and FPN

* Adding support of FasterRCNNHeads

* Introduce norm_layers in backbone utils.

* Bigger RPN head + 2x rcnn v2 models.

* Adding gIoU support to retinanet

* Fix assert

* Add back nesterov momentum

* Rename and extend `FastRCNNConvFCHead` to support arbitrary FCs

* Fix linter

* Detection recipe enhancements

* Add back nesterov momentum

* reverting some recently introduced exceptions

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

* address PR comments

* replace one more assert with torch._assert:

* address PR comments

* make type checker happy

* Fix bug

* fix bug

* fix for wrong asserts

* attempt to make tests pass

* Fix test_ops tests

* Fix expected exception in tests

* fix typo

* fix tests and format

* fix flake8

* remove one last exception

* fix error

* remove unused immport

* replace fake returns by else
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* call _upcast to consider overflow

giou loss is weak at overflow problem because it computes area of box.

* cast datatype to float

* add ":" to if

* lint Test for membership should be 'not in' (E713)

* replace most asserts with exceptions

* fix formating issues

* fix linting and remove more asserts

* fix regresion

* fix regresion

* fix bug

* apply ufmt

* apply ufmt

* fix tests

* fix format

* fix None check

* fix detection models tests

* non scriptable any

* add more checks for None values

* fix retinanet test

* fix retinanet test

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

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

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

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

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

* make value checks more pythonic:

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

* make value checks more pythonic

* make more checks pythonic

* fix bug

* appy ufmt

* fix tracing issues

* fib typos

* fix lint

* remove unecessary f-strings

* fix bug

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

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

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

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

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

* address PR comments

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

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

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

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

* address PR comments

* addressing further pr comments

* fix bug

* remove unecessary else

* apply ufmt

* last pr comment

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

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

* 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>

* Consolidating __repr__ strings
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.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

fixes issue #5322
Co-authored-by: Nicolas Granger <nicolas.granger@cea.fr>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.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.

* Remove module vs method name clash

* 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.

* log API v3

* make torchscript happy

* make torchscript happy

* add missing logs to constructor

* log ops C++ API as well

* fix type hint

* check function with isinstance
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* revamp log api usage method

According to the benchmark link https://github.com/pytorch/vision/issues/1311#issuecomment-781329339

, for GPU the threshold should be higher (which is why detectron2 used 40k).
This PR changes the threshold to be device dependent.
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>