GitLab

* Change enum name for weights contributed by community.

* Adding multiweight support to squeezenet.

* improve download nightly pytorch

* update unitest cuda to 11.3

* add nvjpeg in cuda 11.3

* avoid catching exception

* restore to cu111

* Update install.sh

* use conda MatchSpec string

* update linux

* for linux

* Update install.sh
Co-authored-by: Nikita Shulga <nshulga@fb.com>

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

* Adding GoogLeNet with multi-weight support.

* Simplify expression.

* 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>

* Add logging to torchvision ops

* Hack to make torchscript work

* Bugfix

* Bugfix

* Lint

* mypy... let's silence it

* Fighting with mymy

* One more try

Summary:
This diff enables ImageNet to be usable from within torchvision.

It implements a different codepath for some families of datasets that can be sharded into multiple pieces, and uses it if within fbcode.

For now all previously supported datasets are also supported (MNIST, CIFAR and FashionMNIST), in addition to ImageNet.

Pull Request resolved: https://github.com/pytorch/vision/pull/4776

Reviewed By: datumbox

Differential Revision: D31929684

fbshipit-source-id: 58f9fe2ed6ce731a6b43a38be912983247eff562
(cherry picked from commit b43fead8ea5164e37637ade0e80477e94f993365)

* Update readme for new torch

* Fix typo

It's FBcode, not FBCode

* Adding multiweight support for shufflenetv2 prototype models

* Revert "Adding multiweight support for shufflenetv2 prototype models"

This reverts commit 31fadbee7d1a65cd73ae43dfd4ac6e97e7ca7b01.

* Adding multiweight support for shufflenetv2 prototype models

* Revert "Adding multiweight support for shufflenetv2 prototype models"

This reverts commit 4e3d900f796c1e3e667312087e77956ca4a4c017.

* Adding multiweight support for shufflenetv2 prototype models

* addressing PR comment

* Show git diff after lint run

* break both flake8 and ufmt

* Make it run on fail

* Undo breaks and fix job message.

* [WIP] Added script to sync fbcode changes with main branch

* Make unique branches for multiple runs of the script

* Updated the files

* Change echo message

* Addressed review comments

* Removed from_repo command line argument

* Make fork_main_branch optional

* 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

* adding multiweight support for deeplabv3 prototype models

* adding default values for optional params

* fixing bug

* addressing PR comment

* 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.

* cache dataset info

* try loading categories file by default
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Adding multi-weight support to LRASPP

* Adding tests for segmentation models.

* Skip segmentation test by default.

Relocate fails to find nvjpeg unless its present in the library search path.

* Refactoring tests.

* Fixing lint.

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

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

* replace np.frombuffer with torch.frombuffer in MNIST prototype

* cleanup

* appease mypy

* more cleanup

* clarify inplace offset

* fix num bytes for floating point data