GitLab

* Fixing inverted center_crop check on Classification preset

* Remove the `--train-center-crop` flag.

* 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

* added script files

* added cascaded inference evaluation

* added optimizer option

* minor changes

* Update references/depth/stereo/train.py
Co-authored-by: vfdev <vfdev.5@gmail.com>

* adressed some comments

* change if-else to dict

* added manual resizing for masks and disparities during evaluation

* minor fixes after previous changes

* changed dataloader to be initialised once

* added distributed changes

* changed loader logic

* updated eval script to generate weight API like logs

* improved support for fine-tuning / training resume

* minor changes for finetuning

* updated with transforms from main

* logging distributed deadlock fix

* lint fix

* updated metrics

* weights API log support

* lint fix

* added readme

* updated readme

* updated readme

* read-me update

* remove hardcoded paths. improved valid dataset selection and sync

* removed extras from gitignore
Co-authored-by: Joao Gomes <jdsgomes@fb.com>
Co-authored-by: vfdev <vfdev.5@gmail.com>
Co-authored-by: YosuaMichael <yosuamichaelm@gmail.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>

* Added transforms for Stereo Matching

* changed implicit Y scaling to 0.

* Adressed some comments

* addressed type hint

* Added interpolation random interpolation strategy

* Aligned crop get params

* fixed bug in RandomErase

* Adressed scaling and typos

* Adressed occlusion typo

* Changed parameter order in F.erase

* fixed random erase

* Added inference preset transform for stereo matching

* added contiguous reshape to output tensors

* Adressed comments

* Modified the transform preset to use Tuple[int, int]

* adressed NITs

* added grayscale transform, align resize -> mask

* changed max disparity default behaviour

* added fixed resize, changed masking in sparse flow masking

* update to align with argparse

* changed default mask in asymetric pairs

* moved grayscale order

* changed grayscale api to accept to tensor variant

* mypy fix

* changed resize specs

* adressed nits

* added type hints

* mypy fix

* mypy fix

* mypy fix
Co-authored-by: Joao Gomes <jdsgomes@fb.com>

* Moved more losses into classes

* Added photometric loss

* quick fix for ssim loss return value

* added references

* replaced with unsqueeze

* renaming variables

* add ref to consistency loss

* made mask optional everywhere. generalised photometric displacement

* smoothness typo

* fixed flow channel selection bug

* aligned with training script
Co-authored-by: Joao Gomes <jdsgomes@fb.com>

* S3D weight deployment

* Update accuracies.

* Address review comments.

Resolves issue reported at https://github.com/pytorch/vision/commit/6e535db255cee3ce878dd7a54dda01d4ec8932c1#commitcomment-81409388

There seems to be a misspelling on the name of the parameter. This PR updates `total_steps` to `total_iters` which is the correct argument.

* 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>

* Expose on Hub the public methods of the registration API

* Limit methods and update docs.

* Update references to use the new Model Registration API

Update `RandomPhotometricDistort` `__init__` argument to correct types.

* upgrade usort to

* Also update black

* Actually use 1.0.2

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

* Add ensembled video accuracy on video reference script

* Change the parser func to be similar with classification reference

* Fix typo type->dtype

* Use custom kinetics

* Fix dataset to not getting start_pts

* Change dataset name, and put video_idx at the back

* Ufmt format

* Use functional softmax, updating meta and use it to overwrite eval param

* Fix typo

* Put the eval parameters on the docs for now

* Change meta for video resnet to use frame-rate 15, also change wording on docs

* Update the dataset cache to factor in parameters from the args.

* Fix linter

* 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

* added simple POC

* added jitter and crop options

* added references

* moved simplecopypaste to detection module

* working POC for simple copy paste in detection

* added comments

* remove transforms from class
updated the labels
added gaussian blur

* removed loop for mask calculation

* replaced Gaussian blur with functional api

* added inplace operations

* added changes to accept tuples instead of tensors

* - make copy paste functional
- make only one copy of batch and target

* add inplace support within copy paste functional

* Updated code for copy-paste transform

* Fixed code formatting

* [skip ci] removed manual thresholding

* Replaced cropping by resizing data to paste

* Removed inplace arg (as useless) and put a check on iscrowd target

* code-formatting

* Updated copypaste op to make it torch scriptable
Added fallbacks to support LSJ

* Fixed flake8

* Updates according to the review
Co-authored-by: vfdev-5 <vfdev.5@gmail.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* 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

* Dataset creation now supports "new" version of Kinetics dataset

* remove unnecessary warning for now

* provide kinetics option

* new reading somehow doesn't need BHWC to BCHW transform

* Addressing minor comments

* Adding kinetics deprication warning for the old Kinetics400 class

* lint error

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

* Updating README

* Remove BHWC to BCHW

* Put warning back

* formatting
Co-authored-by: Bruno Korbar <bkorbar@quansight.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* add swin_s and swin_b variants

* fix swin_b params

* fix n parameters and acc numbers

* adding missing acc numbers

* apply ufmt

* Updating `_docs` to reflect training recipe

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

* Change code to reduce variance in eval

* Remove unnecessary new line

* Fix missing import warnings

* Fix the warning on video_classification

* Fix bug to get len of UniformClipSampler

* Add shufflenetv2 1.5 and 2.0 weights

* Update recipe

* Add to docs

* Use resize_size=232 for eval and update the result

* Add quantized shufflenetv2 large

* Update docs and readme

* Format with ufmt

* Add to hubconf.py

* Update readme for classification reference

* Fix reference classification readme

* Fix typo on readme

* Update reference/classification/readme

* add swin transformer

* Update swin_transformer.py

* Update swin_transformer.py

* fix lint

* fix lint

* refactor code

* add swin_transformer

* Update swin_transformer.py

* fix bug

* refactor code

* fix lint

* update init_weights

* move shift_window into attention

* refactor code

* fix bug

* Update swin_transformer.py

* Update swin_transformer.py

* fix lint

* add patch_merge

* fix bug

* Update swin_transformer.py

* Update swin_transformer.py

* Update swin_transformer.py

* refactor code

* Update swin_transformer.py

* refactor code

* fix lint

* refactor code

* add swin_tiny

* add swin_tiny.pkl

* fix lint

* Delete ModelTester.test_swin_tiny_expect.pkl

* add swin_tiny

* add

* add Optional to bias

* update init weights

* update init_weights and add no weight decay

* add no weight decay

* add set_weight_decay

* add set_weight_decay

* fix lint

* fix lint

* add lr_cos_min

* add other swin models

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

* refactor doc

* Update utils.py

* Update train.py

* Update train.py

* Update swin_transformer.py

* update model builder

* fix lint

* add

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

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

* update other model

* simplify the model name just like ViT

* add lr_cos_min

* fix lint

* fix lint

* Update swin_transformer.py

* Update swin_transformer.py

* Update swin_transformer.py

* Delete ModelTester.test_swin_tiny_expect.pkl

* add swin_t

* refactor code

* Update train.py

* add swin_s

* ignore a error of mypy

* Update swin_transformer.py

* fix lint

* add swin_b

* add swin_l

* refactor code

* Update train.py

* move relative_position_bias to __init__

* fix formatting

* Revert "fix formatting"

This reverts commit 41faba232668f7ac4273a0cf632c0d0130c7ce9c.

* Revert "move relative_position_bias to __init__"

This reverts commit f0615440bf18617dc0e5dc4839bd5ed27e5ed010.

* refactor code

* Remove deprecated meta-data from `_COMMON_META`

* fix linter

* add pretrained weights for swin_t

* fix format

* apply ufmt

* add documentation

* update references README

* adding new style docs

* update pre-trained weights values

* remove other variants

* fix typo

* Remove expect for the variants not yet supported
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Joao Gomes <jdsgomes@fb.com>

* Minor updates to optical flow ref for consistency

* Actually put back name

* linting

* add set_weight_decay

* Update _utils.py

* refactor code

* fix import

* add set_weight_decay

* fix lint

* fix lint

* replace split_normalization_params with set_weight_decay

* simplfy the code

* refactor code

* refactor code

* fix lint

* remove unused

* Update test_ops.py

* Update train.py

* Update _utils.py

* Update train.py

* add set_weight_decay

* add set_weight_decay

* Update _utils.py

* Update test_ops.py

* Change `--transformer-weight-decay` to `--transformer-embedding-decay`
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>

* 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>

* Change optical flow train.py function name from validate to evaluate so it is similar to other references

* Add --device as parameter and enable to run in non distributed mode

* Format with ufmt

* Fix unneccessary param and bug

* Enable saving the optimizer and scheduler on the checkpoint

* Fix bug when evaluate before resume and save or load model without ddp

* Fix case where --train-dataset is None
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* Refactor preset transforms

* Making presets public.

* Remove from models and references.

* Adding most tests and docs.

* Adding transforms tests.

* Remove unnecesary ipython notebook.

* Simplify tests.

* Addressing comments.

* Extend the EfficientNet class to support v1 and v2.

* Refactor config/builder methods and add prototype builders

* Refactoring weight info.

* Update dropouts based on TF config ref

* Update BN eps on TF base_config

* Use Conv2dNormActivation.

* Adding pre-trained weights for EfficientNetV2-s

* Add Medium and Large weights

* Update stats with single batch run.

* Add accuracies in the docs.

* Replace get_image_size/num_channels with get_image_dims

* Reduce verbosity

* Fix JIT-scriptability

* Refactoring

* More refactoring

* Replace all _FP/_FT direct calls.

* Remove usages of get_image_size and get_image_num_channels from code-base.

* Fix JIT issues

* Adding missing assertion.

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