GitLab

Co-authored-by: Mateusz Guzek <matguzek@meta.com>
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* _weight_size -> _file_size

* Better formatting of individual weights tables

* Remove file size from main tables to avoid confusion with weight size (as in RAM)

* Remove unnecessary (file size) suffix

* Fix CI error?

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

* Adding _ops and _weight_size metadata checks to tests

* Fixing wrong ops value

* Changing test_schema_meta_validation to instantiate the model only once

* moving instantiating quantized models inside get_ops

* Small refactor of test_schema_meta_validation logic

* Reverting to previous ops value

* Simplifying unquantized models logic in test_schema_meta_validation

* Update test/test_extended_models.py
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Toni Blaslov <tblaslov@fb.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Adding FLOPs and size to model metadata

* Adding weight size to quantization models

* Small refactor of rich metadata

* Removing unused code

* Fixing wrong entries

* Adding .DS_Store to gitignore

* Renaming _flops to _ops

* Adding number of operations to quantization models

* Reflecting _flops change to _ops

* Renamed ops and weight size in individual model doc pages

* Linter fixes

* Rounding ops to first decimal

* Rounding num ops and sizes to 3 decimals

* Change naming of columns.

* Update tables
Co-authored-by: Toni Blaslov <tblaslov@fb.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* make weights deepcopyable

* add test

* test enum member instead of whole enum

* Add `handle_legacy_interface()` to all new models.

* Fix imports

* Addressing review comments.

* Fix linter

* Addressing further comments.

* 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>

* Adding MViT v2 architecture (#6105)

* Adding mvitv2 architecture

* Fixing memory issues on tests and minor refactorings.

* Adding input validation

* Adding docs and minor refactoring

* Add `min_temporal_size` in the supported meta-data.

* Switch Tuple[int, int, int] with List[int] to support easier the 2D case

* Adding more docs and references

* Change naming conventions of classes to follow the same pattern as MobileNetV3

* Fix test breakage.

* Update todos

* Performance optimizations.

* Add support to MViT v1 (#6179)

* Switch implementation to v1 variant.

* Fix docs

* Adding back a v2 pseudovariant

* Changing the way the network are configured.

* Temporarily removing v2

* Adding weights.

* Expand _squeeze/_unsqueeze to support arbitrary dims.

* Update references script.

* Fix tests.

* Fixing frames and preprocessing.

* Fix std/mean values in transforms.

* Add permanent Dropout and update the weights.

* Update accuracies.

* Fix documentation

* Remove unnecessary expected file.

* Skip big model test

* Rewrite the configuration logic to reduce LOC.

* Fix mypy

* Remove `(N, T, H, W, C) => (N, T, C, H, W)` conversion on presets

* Update docs.

* Fix the tests

* Use `output_format` for `read_video()`

* Use `output_format` for `Kinetics()`

* Adding input descriptions on presets

* 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.

* Improving the auto-gen doc.

* Adding details for AlexNet, ConvNext, DenseNet, EfficientNets, GoogLeNet and InceptionV3.

* Fixing location of `_docs`

* Adding docs in the remaining classification models.

* Fix linter

* POC

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

* Apply suggestions from code review
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Fix tests

* ufmt

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

* Detection recipe enhancements

* Add back nesterov momentum

* 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>

* renamed ImageNet weights

* renamed COCO weights

* renamed COCO with VOC labels weights

* renamed Kinetics 400 weights

* rename default with DEFAULT

* update test

* fix typos

* update test

* update test

* update test

* indent as w was weight_enum

* revert

* Adding back the capitalization test
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Adding min_size as a required field.

* Adding min_size to classification models (quantized and not)

* Adding min_size to video models meta.

* Moving min_size to _COMMON_META

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

* Improved meta-data for models.

* Addressing comments from code-review.

* Add parameter count.

* Fix linter.

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

* Adding test that verifies meta schema.

* Adding missing interpolation to keypoint model.

* Change assertion.

* Adding map metric in meta schema for detection and renaming metrics for kp and mask rcnn.

* simplify model builders

* cleanup

* refactor kwonly to pos or kw handling

* put weight verification back

* revert num categories checks

* fix default weights

* cleanup

* remove manual parameter map

* refactor decorator interface

* address review comments

* cleanup

* refactor callable default

* fix type annotation

* process ungrouped models

* cleanup

* mroe cleanup

* use decorator for detection models

* add decorator for quantization models

* add decorator for segmentation  models

* add decorator for video  models

* remove old helpers

* fix resnet50

* Adding verification back on InceptionV3

* Add kwargs in DeeplabeV3

* Add kwargs on FCN

* Fix typing on Deeplab

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

* Change the `default` weights mechanism to sue Enum aliases.

* Change `get_weights` to work with full Enum names and make it public.

* Applying improvements from code review.

* Rename classes Weights => WeightsEnum and WeightEntry => Weights.

* Make enum values follow the naming convention `_V1`, `_V2` etc

* Cleanup the Enum class naming conventions.

* Add a test to check naming conventions.

* [vit] Adding ViT to torchvision/models

* adding pre-logits layer + resolving comments

* Fix the model attribute bug

* Change version to arch

* fix failing unittests

* remove useless prints

* reduce input size to fix unittests

* Increase windows-cpu executor to 2xlarge

* Use `batch_first=True` and remove classifier

* Change resource_class back to xlarge

* Remove vit_h_14

* Remove vit_h_14 from __all__

* Move vision_transformer.py into prototype

* Fix formatting issue

* remove arch in builder

* Fix type err in model builder

* address comments and trigger unittests

* remove the prototype import in torchvision.models

* Adding vit back to models to trigger CircleCI test

* fix test_jit_forward_backward

* Move all to prototype.

* Adopt new helper methods and fix prototype tests.

* Remove unused import.
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Vasilis Vryniotis <vvryniotis@fb.com>

* enable caching of model weights for prototype CI

* syntax

* syntax

* make cache dir dynamic

* increase verbosity

* fix

* use larget CI machine

* revert debug output

* [DEBUG] test env var usage in save_cache

* retry

* use checksum for caching

* remove env vars because expansion is not working

* syntax

* cleanup

* base caching on model-urls

* relax regex

* cleanup skips

* cleanup

* fix skipping logic

* improve step name

* benchmark without caching

* benchmark with external download

* debug

* fix manual download location

* debug again

* download weights in the background

* try parallel download

* add missing import

* use correct decoractor

* up resource_class

* fix wording

* enable stdout passthrough to see download during test

* remove linebreak

* move checkout up

* cleanup

* debug failing test

* temp fix

* fix

* cleanup

* fix regex

* remove explicit install of numpy

* Updated the link for densenet recipe.

* Set default value of `num_classes` and `num_keypoints` to `None`

* Provide helper methods for parameter checks to reduce duplicate code.

* Throw errors on silent config overwrites from weight meta-data and legacy builders.

* Changing order of arguments + fixing mypy.

* Make the builders fully BC.

* Add "default" weights support that returns always the best weights.