- 20 Oct, 2021 12 commits
-
-
Nikita Shulga authored
* Move TorchVision conda package to use pytorch-mutex This is follow up after https://github.com/pytorch/builder/pull/823 that gets rids of `feature` and migrate it to `run_constrained` * Update packaging/torchvision/meta.yaml Co-authored-by:
Eli Uriegas <1700823+seemethere@users.noreply.github.com> * Update packaging/torchvision/meta.yaml Co-authored-by:
-
Joao Gomes authored
* Densenet121 added * All densenet prototypes added * fixing flake8 errors * fixing argument type
-
Joao Gomes authored
* adding vgg 11 * adding remaining vgg prototype models * fixing path for vgg16_bn molde Co-authored-by:Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Joao Gomes authored
* adding alexnet prototype model * adding recipe reference * fixing lint Co-authored-by: -
Philip Meier authored
-
Joao Gomes authored
* 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 authored
* 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.
-
Philip Meier authored
-
Philip Meier authored
* add CI job for prototype tests * register prototype job * fix torchvision installation * fix test invocation * ignore prototype tests in normal unittests Co-authored-by: -
Prabhat Roy authored
* Fixed unused variables in ops * Fixed test failure
-
Philip Meier authored
-
Nikita Shulga authored
As of https://github.com/pytorch/pytorch/pull/65649 Windows CUDA-10.2 builds are no longer generated, so lets limit it to 11.3 only
-
- 19 Oct, 2021 7 commits
-
-
Zhiqiang Wang authored
Co-authored-by: -
Vasilis Vryniotis authored
* 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.
-
Philip Meier authored
* streamline category file generation for prototype datasets * cleanup Co-authored-by:Prabhat Roy <prabhatroy@fb.com>
-
Aditya Oke authored
* 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:
Khushi Agrawal <khushiagrawal411@gmail.com> Co-authored-by:
-
Nicolas Hug authored
-
Harish Kulkarni authored
* Updated compatibility matrix to include LTS version * Backed out inadvertent change Co-authored-by: -
Philip Meier authored
-
- 18 Oct, 2021 7 commits
-
-
Philip Meier authored
-
Bruno Korbar authored
* initial commit * initial commit * flake8 * last nits Co-authored-by: -
Vasilis Vryniotis authored
* Fixing minor issue on typing. * Sample implementation for quantized resnet50.
-
Vasilis Vryniotis authored
-
Philip Meier authored
Co-authored-by: -
Joao Gomes authored
* adding test for trainable paramters in detection models * modifying range of trainable layers Co-authored-by: -
Guo authored
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>
-
- 17 Oct, 2021 1 commit
-
-
Dmytro authored
-
- 15 Oct, 2021 5 commits
-
-
Kai Zhang authored
-
Aditya Oke authored
* Annotate rpn * Small fix * Small fix and ignore Co-authored-by: -
Nicolas Hug authored
-
Vasilis Vryniotis authored
* Adding FasterRCNN ResNet50. * Refactoring to remove duplicate code. * Adding typing info. * Setting weights_backbone=None as default value. * Overwrite eps only for specific weights.
-
Francisco Massa authored
* Add scripts for facilitating generating release notes * remove unused lists, and added instructions, applied balck * renamed file * Added pandas script directly Co-authored-by:
Nicolas Hug <nicolashug@fb.com> Co-authored-by:
Nicolas Hug <contact@nicolas-hug.com>
-
- 14 Oct, 2021 2 commits
-
-
Nicolas Hug authored
-
Vasilis Vryniotis authored
* 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.
-
- 13 Oct, 2021 4 commits
-
-
Nicolas Hug authored
-
Muhammed Abdullah authored
* 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: -
Jirka Borovec authored
Co-authored-by:
deepsource-autofix[bot] <62050782+deepsource-autofix[bot]@users.noreply.github.com> Co-authored-by:
-
Joao Gomes authored
* 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:
-
- 12 Oct, 2021 2 commits
-
-
Aditya Oke authored
* Add typing for imagelist, move params to docstring * Add docs
-
Aditya Oke authored
* 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:
-
