GitLab

* Enabling exporting symbols on windows

Small fix to allow for the built library to be used in windows #728

* added macro to allow for exported symbols on windows

* added macro to allow for exported symbols on windows

* removed cmake command

* added dllimport using torchvision_EXPORTS preprocessor

I grepped the repo for Ouputs and these were the only occurences

* added a generic test for the datasets

* addressed requested changes

- renamed generic*() to generic_classification*()
- moved function inside Tester
- test class_to_idx attribute outside of generic_classification*()

* can't work with pytorch-cpu fixed

utils.py can't work with pytorch-cpu because of this line of code `memory=torch.cuda.max_memory_allocated()`

* can't work with pytorch-cpu fixed

utils.py can't work with pytorch-cpu because of this line of code 'memory=torch.cuda.max_memory_allocated()'

* Fix normalize for different dtype than float32

* Fix lint

Change documentation of perspective(). The doc was about an old version that used directly transformation parameters

* Raise error during downloading

* Fix py2 error and lint

* create imagenet fakedata on-the-fly

* flake8

* Minor test refactorings (#1011)

* Make tests work on fbcode

* Lint

* Fix rebase error

* Properly use get_file_path_2

* Fix wrong use of get_file_path_2 again

* Missing import

* create imagenet fakedata on-the-fly

* Make tests work on fbcode

* Lint

* Fix rebase error

* Properly use get_file_path_2

* Fix wrong use of get_file_path_2 again

* Missing import

* added test for CIFAR10(0)

* create CIFAR data on-the-fly

* flake8

* fixed typo

* removed falsely added import

* Added general reader for sn3 tensors in "pascalvincent" format

* Added class QMNIST into mnist.py

* QMNIST dataset: make some pt files smaller

* Change request from fmassa.

* read_sn3_pascalvincent_tensor: cse

* read_sn3_pascalvincent_tensor: check file size (when strict!=False)

* Fix lint

* More lint

* Add documentation and expose QMNIST to dataset namespace

This PR uses a protected method for loading and initializing the segmentation models. Relevant #875

* CelebA: track attr names, support split="all", code cleanup

* fix typo

* Added the existing code

* Added squeezenet and fixed some stuff in the other models

* Wrote DenseNet and a part of InceptionV3

Going to clean and check all of the models and finish inception

* Fixed some errors in the models

Next step is writing inception and comparing with python code again.

* Completed inception and changed models directory

* Fixed and wrote some stuff

* fixed maxpoool2d and avgpool2d and adaptiveavgpool2d

* Fixed a few stuff

Moved cmakelists to root and changed the namespace to vision and wrote weight initialization in inception

* Added models namespace and changed cmakelists

the project is now installable

* Removed some comments

* Changed style to pytorch style, added some comments and fixed some minor errors

* Removed truncated normal init

* Changed classes to structs and fixed a few errors

* Replaced modelsimpl structs with functional wherever possible

* Changed adaptive average pool from struct to function

* Wrote a max_pool2d wrapper and added some comments

* Replaced xavier init with kaiming init

* Fixed an error in kaiming inits

* Added model conversion and tests

* Fixed a typo in alexnet and removed tests from cmake

* Made an extension of tests and added module names to Densenet

* Added python tests

* Added MobileNet and GoogLeNet models

* Added tests and conversions for new models and fixed a few errors

* Updated Alexnet ad VGG

* Updated Densenet, Squeezenet and Inception

* Added ResNexts and their conversions

* Added tests for ResNexts

* Wrote tools nessesary to write ShuffleNet

* Added ShuffleNetV2

* Fixed some errors in ShuffleNetV2

* Added conversions for shufflenetv2

* Fixed the errors in test_models.cpp

* Updated setup.py

* Fixed flake8 error on test_cpp_models.py

* Changed view to reshape in forward of ResNet

* Updated ShuffleNetV2

* Split extensions to tests and ops

* Fixed test extension

* Fixed image path in test_cpp_models.py

* Fixed image path in test_cpp_models.py

* Fixed a few things in test_cpp_models.py

* Put the test models in evaluation mode

* Fixed registering error in GoogLeNet

* Updated setup.py

* write test_cpp_models.py with unittest

* Fixed a problem with pytest in test_cpp_models.py

* Fixed a lint problem

Changes made in 7716aba5 broke calls to this method.

* GPU efficient Densenets

* removed `import math`

* Changed 'efficient' to 'memory_efficient'

* Add tests

* Bugfix in test

* Fix lint

* Remove unecessary formatting

* allow user to define residual settings

* 4spaces

* linting errors

* backward compatible, and added test

* adding mixed precision training with Apex

* fix APEX default optimization level

* adding python version check for apex

* fix LINT errors and raise exceptions if apex not available

* updating docs for randomperspective

* my

* ci

* added fake data

* fixed fake data

* renamed extract and download methods and added functionality

* added raw fake data

* refactored imagenet and added test

* flake8

* added fake devkit and mocked download_url

* reversed uncommenting

* added mock to CI

* fixed tests for imagefolder

* flake8

Add 'import torch' in example

* add more hub models

* fix lint

* make C extension lazy-import

* add lazy loading to roi_pool

* modif of the STL10 loader

* missing space

* Fix STL10 repr

* Do not inherit from Cifar10

* Make it safer to inherit from VisionDataset

* WIP

* WIP: minor improvements

* Add tests

* Fix typo

* Use download_and_extract on caltech, cifar and omniglot

* Add a print message during extraction

* Remove EMNIST from test

* add USPS dataset

* minor fixes

* Improvements to the USPS dataset

Add it to the documentation, expose it to torchvision.datasets
and inherit from VisionDataset