GitLab

Following a similar line of inquiry to pytorch/audio#217

* [WIP] Minor cleanups on R3d

* Move all models to video/resnet.py

* Remove old files

* Make tests less memory intensive

* Lint

* Fix typo and add pretraing arg to training script

* Move RandomClipSampler to references

* Lint and bugfix

* Optimize read_video_timestamps for some formats

* Add some tests

* Miscellaneous fixes and improvements

* Guard against videos without video stream

* Fix lint

* Add test for packed b-frames videos

* Fix missing import

* [0.4_video] models - initial commit

* addressing fmassas inline comments

* pep8 and flake8

* simplify "hacks"

* sorting out latest comments

* nitpick

* Updated tests and constructors

* Added docstrings - ready to merge

* introduced function to verify str arguments

* flake8

* added FIXME to VOC

* Fixed error message

* added test for verify_str_arg

* cleanup todos

* added option for custom error message

* fix VOC

* fixed Caltech

Also extend video saving to support different codecs and options. Notably, we can now save with lossless compression

* in_channels_stage2 from backbone.inplanes

* remove type for backward compatible

* Add VideoClips and Kinetics dataset

* Lint + add back missing line

* Adds ClipSampler following Bruno comment

* Change name following Bruno's suggestion

* Enable specifying a target framerate

* Fix test_io for new interface

* Add comment mentioning drop_last behavior

* Make compute_clips more robust

* Flake8

* Fix for Python2

* Added mnasnet

* Fixed some stuff

* Fixed some stuff

* Finished MNASNet

* Fixed format error

* Fixed format error

* cast images to PIL at instantiation instead of runtime

* add test for svhn

* added tests for remaining SVHN splits

* flake8

* rolled back changes to datasets

* to_pil_image updates

* lint

* Update test_transforms.py

* Update test_transforms.py

* Fix bug to Random Erasing

1. Avoid forever loop for getting parameters of erase.
2. replace' img_b' by 'img_c', because it indicates the channel.
3. replace v = torch.rand([img_c, h, w]) by v = torch.empty([img_c, h, w], dtype=torch.float32).normal_(). Normally distributed achieves better performance.

* add test

* Update test_transforms.py

* Update transforms.py

* Update test_transforms.py

* Update transforms.py

* Update functional.py

* Update test for detection model to test input list unmodified

Update test for detection model to test input list unmodified according to suggestion in a previous PR

* test input unchaged

* Cityscapes test; semantic segmentation getitem test

* Add multiple targets test for Cityscapes

* flake8 fix for test_datasets

* initial commit

* add more checks, fix lint, fix doc

* WIP

* WIP

* Add some documentation

* Improve tests and add GC collection

* [WIP] add timestamp getter

* Bugfixes

* Improvements and travis

* Add audio fine-grained alignment

* More doc

* Remove unecessary file

* Remove comment

* Lazy import av

* Remove hard-coded constants for the test

* Return info stats from read

* Fix for Python-2

* updates on normalize

* test fixes

* Update test_transforms.py

* test improved

* Update test_transforms.py

* behaviour changes RandomErasing

* test fixes

* linter fix

* fix save_image when height or width == 1

* test_save_image_single_pixel

* add erase function

* add Random Erasing

* Update transforms.py

* Update transforms.py

* add test for random erasing

* Update test_transforms.py

* fix flake8

* Update test_transforms.py

* Update functional.py

* Update test_transforms.py

* fix bug for per-pixel erasing

* Update transforms.py

* specific for coordinate (x, y)

* add raise TypeError for img

* Update transforms.py

* Update transforms.rst

* fix:error message of to_tensor

The error "pic should be PIL Image or ndarray. Got '<numpy.ndarray>'" is confusing.

* fix:a clearer function name

_is_numpy_image is clearer than _is_numpy_image_dim

* fix:add a test case

Add a test case in test/test_transforms.py to test the error message

* fix:pass ci check

* fix:wrong random matrix

* 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*()

* Fix normalize for different dtype than float32

* Fix lint

* 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 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

* 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

* 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