GitLab

* add prototype features

* add some JIT tests

* refactor input data handling

* refactor tests

* cleanup tests

* add BoundingBox feature

* mypy

* xfail torchscript tests for now

* cleanup

* fix imports

* add tests for builtin prototype datasets

* fix caltech101

* fix emnist

* fix mnist and variants

* add iopath as test requirement

* fix MNIST warning

* fix qmnist data generation

* fix cifar data generation

* add tests for imagenet

* cleanup

* modify processPacket to support fast seek

* add fastSeek to ProcessPacket decoder definition

* add fastseek flag to DecoderParametersStruct

* add fastseek flag to the process packet call

* no default params in C++ implementation

* enable flag in C++ implementation

* make order of parameters more normal

* register new seek with python api

* [somewhat broken] test suite for keyframes using pyav

* revert " changes

* add type annotations to init

* Adding tests

* linter

* Flake doesn't show up :|

* Change from unitest to pytest syntax

* add return type
Co-authored-by: Prabhat Roy <prabhatroy@fb.com>

* Reordering the builders to use proper typing.

* Adding additional meta-data on existing quantized models.

* Fixing meta on unquantized model.

* Adding quantized googlenet builder.

* undo inception move.

* Adding recipe information.

* Aligning exception with all other models.

* Adding prototype preprocessing on video references.

* Adding the rest of model builders on faster_rcnn.

* Adding multi-weight support to Quantized ResNet.

* Update references script to support testing quantized models with the new API.

* Handle quantized models correctly in ref script.

* Fixing references for quantization.

* add tests for prototype datasets API

* add pytest-mock as test dependency

* remove unnecessary fixtures

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

* address first batch of review comments

* remove dynamic class generation

* aggregate similar tests

* split immutable tests once again

* removed unused fixture

* remove re.escape usages

* fix dataset mock
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

* adding multiweight support for deeplabv3 prototype models

* adding default values for optional params

* fixing bug

* addressing PR comment

* fixing seed in test_batched_nms_implementations

* change seeds in test_batched_nms_implementations

* change seeds in test_batched_nms_implementations

* Add mutli-weight support for VideoResNet.

* Fix linter.

* Minor refactoring.

* Update comments.

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

* setting 100 seeds

* back to 10 seeds

* Trying with 100 seeds

* Change seeds from 100 to 10

* setting 100 seeds, let's see if it fails

* Passed with 100, so setting 10

* Change test_random_apply

* Change test_random_choice

* Change test_randomness

* took care of RandomVert/HorizFlip

* take care of RandomGrayScale

* minor cleanup

* avoid 0 degree rotation just in case

* Fix flakiness on the TestStochasticDepth test.

* Fix minor bug when p=1.0

* Remove device and dtype setting.

* Adding multi-weight support to LRASPP

* Adding tests for segmentation models.

* Skip segmentation test by default.

* Refactoring tests.

* Fixing lint.

* Skip tests for models that don't have weights.

* Update model checkpoint for resnet50.

* Add get_weight method to retrieve weights from name.

* Update the references to support prototype weights.

* Fixing mypy typing.

* Switching to a python 3.6 supported equivalent.

* Add unit-test.

* Add optional num_classes.

* 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.

* WIP

* cleaner code

* Add tests

* Add docs

* Assert dtype

* put back check

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

* adding Weights classes for Resnet classification models

* Replacing BasicBlock by Bottleneck in all but 3 model contructors

* adding tests for prototype models

* fixing typo in environment variable

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

* changing default value for PYTORCH_TEST_WITH_PROTOTYPE

* adding checks to compare outputs of the prototype vs old models

* refactoring prototype tests

* removing unused imports

* applying ufmt

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

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

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

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

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

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

* Update test/test_prototype_models.py
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.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 CI job for prototype tests

* register prototype job

* fix torchvision installation

* fix test invocation

* ignore prototype tests in normal unittests
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* adding test for trainable paramters in detection models

* modifying range of trainable layers
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* adding tests to check output of quantized models

* adding test quantized model weights

* merge test_new_quantized_classification_model with test_quantized_classification_model

* adding skipif removed by mistake

* addressing comments from PR

* removing unused argument

* fixing lint errors

* changing model to eval model and updating weights

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

* enforce single test in circleci

* changing random seed

* updating weights for new seed

* adding missing empty line

* try 128 random seed

* try 256 random seed

* try 16 random seed

* disable inception_v3 input/output quantization tests

* removing ModelTester.test_inception_v3_quantized_expect.pkl

* reverting temporary ci run_test.sh changes
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

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

* Add str param

* Update test to include str

* Fix mypy

* Remove a small bracket

* Test more robustly

* Update docstring and test:

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

* Update torchvision/utils.py

Small docstring fix

* Update torchvision/utils.py

* remove unnecessary renaming
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Nicolas Hug <nicolashug@fb.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>

* draft commit

* Polish and add corresponding test

* Update docs

* Update torchvision/models/feature_extraction.py

* Update docs/source/feature_extraction.rst
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* initial code

* add SqueezeExcitation

* initial code

* add SqueezeExcitation

* add SqueezeExcitation

* regnet blocks, stems and model definition

* nit

* add fc layer

* use Callable instead of Enum for block, stem and activation

* add regnet_x and regnet_y model build functions, add docs

* remove unused depth

* use BN/activation constructor and ConvBNActivation

* add expected test pkl files

* allow custom activation in SqueezeExcitation

* use ReLU as the default activation

* initial code

* add SqueezeExcitation

* initial code

* add SqueezeExcitation

* add SqueezeExcitation

* regnet blocks, stems and model definition

* nit

* add fc layer

* use Callable instead of Enum for block, stem and activation

* add regnet_x and regnet_y model build functions, add docs

* remove unused depth

* use BN/activation constructor and ConvBNActivation

* reuse SqueezeExcitation from efficientnet

* refactor RegNetParams into BlockParams

* use nn.init, replace np with torch

* update README

* construct model with stem, block, classifier instances

* Revert "construct model with stem, block, classifier instances"

This reverts commit 850f5f3ed01a2a9b36fcbf8405afd6e41d2e58ef.

* remove unused blocks

* support scaled model

* fuse into ConvBNActivation

* make reset_parameters private

* fix type errors

* fix for unit test

* add pretrained weights for 6 variant models, update docs

* Add autouse fixture to save and reset RNG in tests

* Add other RNG generators

* delete freeze_rng_state

* Hopefully fix GaussianBlur test

* Alternative fix, probably better

* revert changes to test_models
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

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

* update channels parameter to every calling to check_functional_vs_PIL_vs_scripted

* update adjust_saturation

* update docstrings for functional transformations

* parametrize channels

* update docstring of ColorJitter class

* move channels to class's parameter

* remove testing channels for geometric transforms

* revert redundant changes

* revert redundant changes

* update grayscale test cases for randaugment, autoaugment, trivialaugment

* update docstrings of randaugment, autoaugment, trivialaugment

* update docstring of ColorJitter

* fix adjust_hue's docstring

* change test equal tolerance

* refactor grayscale tests

* make get_grayscale_test_image private