GitLab

* Add mutli-weight support for FCN.

* Rename base_size to resize_size.

* Adding multiweight support for mnasnet prototype

* Adressing PR comments

* adding return type to _mnasnet
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Adding multiweight support for mobilenetv3 prototype

* 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.

* adding efficientnet to prototype

* Removing _efficientnet_conf from prototype and main efficientnet classification models

* fixing merge conflicts

* fixing merge conflicts

* fixing lint errors

* fixing lint errors

* fixing lint errors

* adding efficientnet to prototype

* renaming _efficientnet_model in torchvision.model to be aligned with prototype implementation

* adding specific cop sizes to ech model

* adding specific cop and resize transforms

* fixing lint errors

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

* rename pretrained model versions
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* rename pretrained model versions
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* rename pretrained model versions
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* rename pretrained model versions
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* rename pretrained model versions
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* rename pretrained model versions
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* rename pretrained model versions
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* rename pretrained model versions
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

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

* adding interpolation model information to all classification prototype models

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

* Migrate mnist dataset from np.frombuffer

* Add a copy with bytearray for non-writable buffers

* Add byte reversal for mnist
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* make mypy more strict for prototype datasets

* fix code format

* apply strictness only to datasets

* fix more mypy issues

* cleanup

* fix mnist annotations

* refactor celeba

* warn on redundant casts

* remove redundant cast

* simplify annotation

* fix import

* WIP

* cleaner code

* Add tests

* Add docs

* Assert dtype

* put back check

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

* add prototype imagenet dataset

* add missing checksums

* fix mypy

* add human readable categories

* cleanup

* sort categories ascending based on wnid

* remove accidentally added file

* cleanup category file generation

* fix mypy

* fix category file inclusion

* fix deprecated import

* Densenet121 added

* All densenet prototypes added

* fixing flake8 errors

* fixing argument type

* adding vgg 11

* adding remaining vgg prototype models

* fixing path for vgg16_bn molde
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* adding alexnet prototype model

* adding recipe reference

* fixing lint
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.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.

* Fixed unused variables in ops

* Fixed test failure

* Move FCN methods to itsown package.

* Fix lint.

* Move LRASPP methods to their own package.

* Move DeepLabV3 methods to their own package.

* Adding deprecation warning for torchvision.models.segmentation.segmentation.

* Refactoring deeplab.

* Setting aux default to false.

* Fixing imports.

* Passing backbones instead of backbone names to builders.

* Fixing mypy

* Addressing review comments.

* Correcting typing.

* Restoring special handling for references.

* streamline category file generation for prototype datasets

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

* Start adding types

* add typing

* Type prototype models

* fix optional type bug

* transient import

* Fix weights type

* fix import

* Apply suggestions from code review

Address nits
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Khushi Agrawal <khushiagrawal411@gmail.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* initial commit

* initial commit

* flake8

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

* Fixing minor issue on typing.

* Sample implementation for quantized resnet50.

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

We no longer cache the data in a custom binary, but simply read from the raw data directly.
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Annotate rpn

* Small fix

* Small fix and ignore
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Adding FasterRCNN ResNet50.

* Refactoring to remove duplicate code.

* Adding typing info.

* Setting weights_backbone=None as default value.

* Overwrite eps only for specific weights.

* Adding lightweight API for models.

* Adding resnet50.

* Fix preset

* Add fake categories.

* Fixing mypy.

* Add string=>weight conversion support on Enums.

* Temporarily hardcoding imagenet categories.

* Minor refactoring.

* Added Dropout parameter of Models

* Added argument description for dropout in MobileNet v2 and v3
Updated quantization/googlenet.py as per the changes in constructor in googlenet

* Moved new dropout parameter n the end

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

Co-authored-by: deepsource-autofix[bot] <62050782+deepsource-autofix[bot]@users.noreply.github.com>
Co-authored-by: deepsource-autofix[bot] <62050782+deepsource-autofix[bot]@users.noreply.github.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Add typing for imagelist, move params to docstring

* Add docs