- 25 Oct, 2021 8 commits
-
-
Prabhat Roy authored
* Removed unnecessary if from setup.py * Removed empty line
-
Vasilis Vryniotis authored
* 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.
-
Francisco Massa authored
Summary: As titled. Reviewed By: sallysyw Differential Revision: D31813675 fbshipit-source-id: 8ff879be172530bcc41aae5d71c67e1e90f09cbf Co-authored-by:Kai Zhang <kaizh@fb.com>
-
Francisco Massa authored
* 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: -
Francisco Massa authored
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:
-
Nicolas Hug authored
-
Vasilis Vryniotis authored
* Add mutli-weight support for FCN. * Rename base_size to resize_size.
-
Nicolas Hug authored
-
- 24 Oct, 2021 1 commit
-
-
puhuk authored
* Add type to default argument To resolve issue #4694 * Resolve issue #4694 Add missing types on argument parser * Update with ufmt formatted with ufmt * Updated with review Updated with review * Update type of arguments Add train.py from video_classification, similarity and train_quantization.py Co-authored-by:Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
- 22 Oct, 2021 6 commits
-
-
Joao Gomes authored
* Adding multiweight support for mnasnet prototype * Adressing PR comments * adding return type to _mnasnet Co-authored-by: -
Nikita Shulga authored
GPU tests have special step to install the driver, CUDA install step shouldl just install the runtime never Fixes regression introduced by https://github.com/pytorch/vision/pull/4421
-
Joao Gomes authored
* Adding multiweight support for mobilenetv3 prototype
-
Vasilis Vryniotis authored
* 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.
-
Joao Gomes authored
* 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
-
Joao Gomes authored
* 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:
-
- 21 Oct, 2021 9 commits
-
-
Matti Picus authored
-
Joao Gomes authored
* adding interpolation model information to all classification prototype models * fixing lint errors Co-authored-by: -
Sergii Khomenko authored
* Migrate mnist dataset from np.frombuffer * Add a copy with bytearray for non-writable buffers * Add byte reversal for mnist Co-authored-by: -
Philip Meier authored
* 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
-
Vasilis Vryniotis authored
-
Nicolas Hug authored
* WIP * cleaner code * Add tests * Add docs * Assert dtype * put back check * Address comments Co-authored-by:Francisco Massa <fvsmassa@gmail.com>
-
Philip Meier authored
* 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
-
Nicolas Hug authored
-
Philip Meier authored
* fix category file inclusion * fix deprecated import
-
- 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: -
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 4 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:
-
