GitLab

making torchvision ops leaf nodes by default

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

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

Closes #4905
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Clean up unnecessary quant builders and add quant weights for 0.5

* Fixing mypy.

* Moving builder to the bottom to use proper typing.

* Renaming weights.

* Adding quantizated inception builder.

* Correct meta info.

* Fix linter.

* Removing init_weights to avoid exposing it on the class.

* 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.

* Update typing

* Fix bug

* Unblock mypy

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

* Moving original builder at the bottom of the page to use proper typing.

* Adding multiweight support to inception.

* Update doc.

* Move model builder at the bottom of the file, so we can use proper typing.

* Adding GoogLeNet with multi-weight support.

* Simplify expression.

* Add mutli-weight support for VideoResNet.

* Fix linter.

* Minor refactoring.

* Update comments.

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

Summary: As titled.

Reviewed By: sallysyw

Differential Revision: D31813675

fbshipit-source-id: 8ff879be172530bcc41aae5d71c67e1e90f09cbf
Co-authored-by: Kai Zhang <kaizh@fb.com>

* Expand usage logging to detection models

Summary: Track all detection model instantiation.

Reviewed By: sallysyw

Differential Revision: D31741603

fbshipit-source-id: 89467db5d89ea41c5a9ab95d1846264d0a1f4199

* Fix lint
Co-authored-by: Kai Zhang <kaizh@fb.com>

Summary: We would like to track the internal usage of TorchVision components. We're tracking [datasets usage](https://fburl.com/daiquery/dqpmemn3

) now. This diff expand the tracking to all models.

Reviewed By: fmassa

Differential Revision: D31441632

fbshipit-source-id: e26072e582ac9f832c2056307ebf0eccf2ed6c9c
Co-authored-by: Kai Zhang <kaizh@fb.com>

* Adding multiweight support for mobilenetv3 prototype

* 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>

* 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.

* 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.

* 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>

* Fixing minor issue on typing.

* Sample implementation for quantized resnet50.

* 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.

* 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

* Start annotating utils

* checking

* Add annotations at _utils.py

* Remove unnecessary comments.

* re-checked typings

* Update typing

* Ignore small error

* Use optional tensor

* Ignore for JIT
Co-authored-by: Khushi Agrawal <khushiagrawal411@gmail.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* Use FX feature extractor for segm model

* Removed use_fe option

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

* add best weights and x_1_6, x_3_2, y_1_6, y_3_2, y_32 weights

* add best weights and x_1_6, x_3_2, y_1_6, y_3_2, y_32 weights

* add weights for x_16gf, x_32gf, y_16gf