GitLab

* 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>

* Add bias parameter to ConvNormActivation

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

making torchvision ops leaf nodes by default

* refactoring methods from MultiScaleRoIAlign

* Expose misc ops at package level

* Adding documentation to the ops exposed

* Add logging to torchvision ops

* Hack to make torchscript work

* Bugfix

* Bugfix

* Lint

* mypy... let's silence it

* Fighting with mymy

* One more try

Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* Fix flakiness on the TestStochasticDepth test.

* Fix minor bug when p=1.0

* Remove device and dtype setting.

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

* Update EMA every X iters.

* Adding AdamW optimizer.

* Adjusting EMA decay scheme.

* Support custom weight decay for Normalization layers.

* Fix identation bug.

* Change EMA adjustment.

* Quality of life changes to faciliate testing

* ufmt format

* Fixing imports.

* Adding FixRes improvement.

* Support EMA in store_model_weights.

* Adding interpolation values.

* Change train_crop_size.

* Add interpolation option.

* Removing hardcoded interpolation and sizes from the scripts.

* Fixing linter.

* Incorporating feedback from code review.

* Fixed unused variables in ops

* Fixed test failure

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

* 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>

* 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.

Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* ops.masks_to_bounding_boxes

* test fixtures

* unit test

* ignore lint e201 and e202 for in-lined matrix

* ignore e121 and e241 linting rules for in-lined matrix

* draft gallery example text

* removed type annotations from pytest fixtures

* inlined fixture

* renamed masks_to_bounding_boxes to masks_to_boxes

* reformat inline array

* import cleanup

* moved masks_to_boxes into boxes module

* docstring cleanup

* updated docstring

* fix formatting issue

* gallery example

* use torch

* use torch

* use torch

* use torch

* updated docs and test

* cleanup

* updated import

* use torch

* Update gallery/plot_repurposing_annotations.py
Co-authored-by: Aditya Oke <47158509+oke-aditya@users.noreply.github.com>

* Update gallery/plot_repurposing_annotations.py
Co-authored-by: Aditya Oke <47158509+oke-aditya@users.noreply.github.com>

* Update gallery/plot_repurposing_annotations.py
Co-authored-by: Aditya Oke <47158509+oke-aditya@users.noreply.github.com>

* Autodoc

* use torch instead of numpy in tests

* fix build_docs failure

* Closing quotes.
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Aditya Oke <47158509+oke-aditya@users.noreply.github.com>

* Updated annotation to be a Union of Tensor and List

* Updated check_roi_boxes_shape.

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

* 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.

* 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>

* correct the size of returne tensor

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

* Edited roi transforms docs

* remove incorrect param desc

* Fixed confusion  about feature maps according to comment

* WIP

* clang

* docs

* extracted out common utils

* Use better quantization function and pass tensors as parameters

* proper dequantization

* Some tests

* Dequantization optimization, seems to gain a few ms

* clang-format

* again

* more correct test. Had to remove optimization although it almost works

* Also test aligned=True

* remove useless part

* more docs and comments

* Put back optimization with more robust test

* Added check for index upper bound

* avoid possible overflow

* Move common function into common.h

* oops

* scale=1,zero_point=0 makes more sense

* Force batch size of 1 to prevent any indexingbug

* format

* format again

* updated docstring

* put back description comment for pre_calc_bilinear_interpolate

* revert most changes to docstring as it's taken care of in another PR

* some doc improvements

* flake8
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* add tests

* fix bug

* remove tests

* fix comment

* fix comment

* add warning

* fix syntax error

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