GitLab

* Model registration mechanism.

* Add overwrite options to the dataset prototype registration mechanism.

* Adding example models.

* Fix module filtering

* Fix linter

* Fix docs

* Make name optional if same as model builder

* Apply updates from code-review.

* fix minor bug

* Adding getter for model weight enum

* Support both strings and callables on get_model_weight.

* linter fixes

* Fixing mypy.

* Renaming `get_model_weight` to `get_model_weights`

* Registering all classification models.

* Registering all video models.

* Registering all detection models.

* Registering all optical flow models.

* Fixing mypy.

* Registering all segmentation models.

* Registering all quantization models.

* Fixing linter

* Registering all prototype depth perception models.

* Adding tests and updating existing tests.

* Fix linters

* Fix tests.

* Add beta annotation on docs.

* Fix tests.

* Apply changes from code-review.

* Adding documentation.

* Fix docs.

* upgrade usort to

* Also update black

* Actually use 1.0.2

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

* Add new .. betastatus:: directive to document Beta APIs

* Also add it for the fine-grained video API

* Add directive for all builders and pages of Detection module

* Also segmentation and video models

* Classif models

* Detection

* Segmentation

* quantization

* Video

* optical flow

* tests

* Fix docs

* Fix Video dataset

* Consistency for RAFT dataset names

* use ImageNet-1K

* Use COCO-val2017-VOC-labels for segmentation

* formatting

* Adding docs for quantized models.

* Adding docs for video models.

* Adding docs for segmentation models.

* Adding docs for optical flow models.

* Adding docs for detection models.

* Fix typo.

* Make changes from code-review.

* Reinstate and deprecate `model_urls` and `quant_model_urls`

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

* Move todo location

* Add alexnet

* Add densenet

* Add efficientnet

* Add googlenet.

* Add inception.

* Add mobilenetv3

* Add regnet

* Add resnet

* Add shufflenetv2

* Fix linter

* Add squeezenet

* Add vgg

* Add vit

* Add quantized googlenet

* Add quantized inceptionv3

* Add quantized mobilenet_v3

* Add quantized resnet

* Add quantized shufflenetv2

* Fix incorrect imports

* Add faster_rcnn

* Add fcos

* Add keypoint rcnn

* Add mask rcnn

* Add retinanet

* Add ssd

* Add ssdlite

* Add deeplabv3

* Add fcn

* Add lraspp.

* Add video resnet

* Removing weights for shufflenetv2_x1.5 and shufflenetv2_x2.0

* Update the comments
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* init

* init

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

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

* Restructuring metrics meta-data for detection, segmentation and optical flow.

* Renaming acc to pixel_acc for segmentation

* Restructure video meta-data.

* Restructure classification and quantization meta-data.

* Fix tests.

* Fix documentation

* Removing `task`, `architecture` and `quantization`

* Fix mypy

* Remove size field

* Remove unused import.

* Fix mypy

* Remove size from schema list.

* update todo

* Simplify with assert

* Adding min_size to all models.

* Update RAFT min size to 128

* Remove publication_year and interpolation meta

* Add type to _COMMON_META and _COMMON_SWAG_META to prevent error from mypy check

* Remove test to check interpolation and publication_year meta
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Add FasterRCNN improved weights

* Add recipe URL

* Update publication_year field

* 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>

* 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>

* 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>

Closes #4905
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

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

* Refactoring resnet_fpn backbone building.

* Passing the change to *_rcnn and retinanet.

* Applying for faster_rcnn + mobilenetv3

* Applying for ssdlite + mobilenetv3

* Applying for ssd + vgg16

* Update the expected file of retinanet_resnet50_fpn to fix order of initialization.

* Adding full model weights for the VGG16 features.

* 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>

* Added paper references to detection models

* Ignore linter warning

* Break long line into two

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

* Specify coordinate constraints

* some more

* flake8

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

* Tag fasterrcnn mobilenetv3 model with 320, add new inference config that makes it 2x faster sacrificing a bit of mAP.

* Add a high resolution fasterrcnn mobilenetv3 model.

* Update tests and expected values.

* Minor refactoring of a private method to make it reusuable.

* Adding a FasterRCNN + MobileNetV3 with & w/o FPN models.

* Reducing Resolution to 320-640 and anchor sizes to 16-256.

* Increase anchor sizes.

* Adding rpn score threshold param on the train script.

* Adding trainable_backbone_layers param on the train script.

* Adding rpn_score_thresh param directly in fasterrcnn_mobilenet_v3_large_fpn.

* Remove fasterrcnn_mobilenet_v3_large prototype and update expected file.

* Update documentation and adding weights.

* Use buildin Identity.

* Fix spelling.

* Introduce small score threshold on rpn

* Adding docs and fixing keypoint and mask.

* Making value 0.0 by default for BC.

* Fixing for onnx.

* Update threshold.

* Removing non-default threshold from reference scripts.
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Fixing trainable_layers bug.

* minor doc fixes

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

* Remove model download from tests

* Refactor trainable_layers checks in detection models

* Bugfix

* Finish tests and fixes

* Fix lint

* Overwriting FrozenBN eps=0.0 if pretrained=True for detection models.

* Moving the method to detection utils and adding comments.

* Add rough implementation of RetinaNet.

* Move AnchorGenerator to a seperate file.

* Move box similarity to Matcher.

* Expose extra blocks in FPN.

* Expose retinanet in __init__.py.

* Use P6 and P7 in FPN for retinanet.

* Use parameters from retinanet for anchor generation.

* General fixes for retinanet model.

* Implement loss for retinanet heads.

* Output reshaped outputs from retinanet heads.

* Add postprocessing of detections.

* Small fixes.

* Remove unused argument.

* Remove python2 invocation of super.

* Add postprocessing for additional outputs.

* Add missing import of ImageList.

* Remove redundant import.

* Simplify class correction.

* Fix pylint warnings.

* Remove the label adjustment for background class.

* Set default score threshold to 0.05.

* Add weight initialization for regression layer.

* Allow training on images with no annotations.

* Use smooth_l1_loss with beta value.

* Add more typehints for TorchScript conversions.

* Fix linting issues.

* Fix type hints in postprocess_detections.

* Fix type annotations for TorchScript.

* Fix inconsistency with matched_idxs.

* Add retinanet model test.

* Add missing JIT annotations.

* Remove redundant model construction

Make tests pass

* Fix bugs during training on newer PyTorch and unused params in DDP

Needs cleanup and to add back support for images with no annotations

* Cleanup resnet_fpn_backbone

* Use L1 loss for regression

Gives 1mAP improvement over smooth l1

* Disable support for images with no annotations

Need to fix distributed first

* Fix retinanet tests

Need to deduplicate those box checks

* Fix Lint

* Add pretrained model

* Add training info for retinanet
Co-authored-by: Hans Gaiser <hansg91@gmail.com>
Co-authored-by: Hans Gaiser <hans.gaiser@robovalley.com>
Co-authored-by: Hans Gaiser <hans.gaiser@robohouse.com>

* freeze layers only if pretrained backbone is used

If pretrained backbone is not used and one intends to train the entire network from scratch, no layers should be frozen.

* function argument to control the trainable features

Depending on the size of dataset one might want to control the number of tunable parameters in the backbone, and this parameter in hyper parameter optimization for the dataset. It would be nice to have this function support this.

* ensuring tunable layer argument is valid

* backbone freezing in fasterrcnn_resnet50_fpn

Handle backbone freezing in fasterrcnn_resnet50_fpn function rather than the resnet_fpn_backbone function that it uses to get the backbone.

* remove layer freezing code

layer freezing code has been moved to fasterrcnn_resnet50_fpn function that consumes resnet_fpn_backbone function.

* correcting linting errors

* correcting linting errors

* move freezing logic to resnet_fpn_backbone

Moved layer freezing logic to resnet_fpn_backbone with an additional parameter.

* remove layer freezing from fasterrcnn_resnet50_fpn

Layer freezing logic has been moved to resnet_fpn_backbone. This function only ensures that the all layers are made trainable if pretrained models are not used.

* update example resnet_fpn_backbone docs

* correct typo in var name

* correct indentation

* adding test case for layer freezing in faster rcnn

This PR adds functionality to specify the number of trainable layers while initializing the faster rcnn using fasterrcnn_resnet50_fpn function. This commits adds a test case to test this functionality.

* updating layer freezing condition for clarity

More information in PR

* remove linting errors

* removing linting errors

* removing linting errors

Co-authored-by: rvirgolireply <51229032+rvirgolireply@users.noreply.github.com>

* Type of input featmap_names fixed in example.

* Added missing imports.

* update doc

* update doc