GitLab

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

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

Update docs to not mention 'registration mechanism' - and move corresponding utils out of Beta (#7142)
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* fix typos throughout the code base

* fix grammar

* revert formatting changes to gallery

* revert 'an uXX'

* remove 'number of the best'

* _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>

* Just start adding mere copy paste

* Replace d with t and D with T

* Align swin transformer video to image a bit

* Rename d -> t

* align with 2d impl

* align with 2d impl

* Add helpful comments and config for 3d

* add docs

* Add docs

* Add configurations

* Add docs

* Fix bugs

* Fix wrong edit

* Fix wrong edit

* Fix bugs

* Fix bugs

* Fix as per fx suggestions

* Update torchvision/models/video/swin_transformer.py

* Fix as per fx suggestions

* Fix expect files and code

* Update the expect files

* Modify video swin

* Add min size and min temporal size, num params

* Add flops and size

* Fix types

* Fix url recipe
Co-authored-by: Yosua Michael Maranatha <yosuamichael@fb.com>

* Fix MaxViT typing

* linter

* 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

* Use the variable name sizes instead of scales for consistency

* Add the missing type hints

* Restore the naming back to scales instead of sizes to avoid backwards incompatibility

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

* Update the expected removal date for several deprecated API

* Revert the change in models/_utils.py

* Remove removal date on pretrained=True

* Update another message related to pretrained=True

* Also update the warning in kwonly_to_pos_or_kw decorator

* Update remaining message in _utils.py

* 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>

* Added maxvit architecture and tests

* rebased + addresed comments

* Revert "rebased + addresed comments"

This reverts commit c5b28398cd48d2f3403c7c8eeefbaba9df05fcfe.

* Re-added model changes after revert

* aligned with partial original implementation

* removed submitit script fixed lint

* mypy fix for too many arguments

* updated old tests

* removed per batch lr scheduler and seed setting

* removed ontap

* added docs, validated weights

* fixed test expect, moved shape assertions in the begging for torch.fx compatibility

* mypy fix

* lint fix

* added legacy interface

* added weight link

* updated docs

* Update references/classification/train.py
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

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

* adressed comments

* update ra_maginuted and augmix_severity default values

* adressed some comments

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

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

* ADD: init_weights config for googlenet

* Fix: Inception and googlenet warnings

* Fix: warning in test_datasets.py

* Fix: Formatting error with ufmt

* Fix: Failing tests in quantized_classification_model

* Update test/test_models.py to make googlenet in 1 line
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Refactor: Change inception quantisation class initialization to use args/kwargs

* Resolve mypy issue

* Move *args before inception_blocks

* Move args keywords before other arguments
Co-authored-by: Ambuj Pawar <your_email@abc.example>
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* crestereo draft implementation

* minor model fixes. positional embedding changes.

* aligned base configuration with paper

* Adressing comments

* Broke down Adaptive Correlation Layer. Adressed some other commets.

* adressed some nits

* changed search size, added output channels to model attrs

* changed weights naming

* changed from iterations to num_iters

* removed _make_coords, adressed comments

* fixed jit test

* config nit

* Changed device arg to str
Co-authored-by: Joao Gomes <jdsgomes@fb.com>
Co-authored-by: YosuaMichael <yosuamichaelm@gmail.com>

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

* Fix imports

* Addressing review comments.

* Fix linter

* Addressing further comments.

Changes image size convention to (h, w). I don't think this is used by
models other than SSD which assumes this convention.
Co-authored-by: Nicolas Granger <nicolas.granger@cea.fr>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* S3D weight deployment

* Update accuracies.

* Address review comments.

* S3D initial commit

* add model builder code and docstrings

* change classifier submodule, populate weights enum

* fix change of block args from List[List[int]] to ints

* add VideoClassification to transforms

* edit weights url for testing, add s3d to models.video init

* norm_layer changes

* norm_layer and args fix

* Overwrite default dropout

* Remove docs from internal submodules.

* Fix tests

* Adding documentation.

* Link doc from main models.rst

* Fix min_temporal_size

* Adding crop/resize parameters in references script

* Release weights.

* Refactor dropout.

* Adding the weights table in the doc
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Vasilis Vryniotis <vvryniotis@fb.com>

* init submit

* fix typo

* support ufmt and mypy

* fix 2 unittest errors

* fix ufmt issue

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

* unify codes

* fix meshgrid indexing

* fix a bug

* fix type check

* add type_annotation

* add slow model

* fix device issue

* fix ufmt issue

* add expect pickle file

* fix jit script issue

* fix type check

* keep consistent argument order

* add support for pretrained_window_size

* avoid code duplication

* a better code reuse

* update window_size argument

* make permute and flatten operations modular

* add PatchMergingV2

* modify expect.pkl

* use None as default argument value

* fix type check

* fix indent

* fix window_size (temporarily)

* remove "v2_" related prefix and add v2 builder

* remove v2 builder

* keep default value consistent with official repo

* deprecate dropout

* deprecate pretrained_window_size

* fix dynamic padding edge case

* remove unused imports

* remove doc modification

* Revert "deprecate dropout"

This reverts commit 8a13f932815ae25655c07430d52929f86b1ca479.

* Revert "fix dynamic padding edge case"

This reverts commit 1c7579cb1bd7bf2f0f94907f39bee6ed707a97a8.

* remove unused kwargs

* add downsample docs

* revert block default value

* revert argument order change

* explicitly specify start_dim

* add small and base variants

* add expect files and slow_models

* Add model weights and documentation for swin v2

* fix lint

* fix end of files line
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Joao Gomes <jdsgomes@fb.com>

* Extending to support MViTv2

* Fix docs, mypy and linter

* Refactor the relative positional code.

* Code refactoring.

* Rename vars.

* Update docs.

* Replace assert with exception.

* Updat docs.

* Minor refactoring.

* Remove the square input limitation.

* Moving methods around.

* Modify the shortcut in the attention layer.

* Add ported weights.

* Introduce a `residual_cls` config on the attention layer.

* Make the patch_embed kernel/padding/stride configurable.

* Apply changes from code-review.

* Remove stale todo.