GitLab

* Initial version of the segmentation examples

WIP

* Cleanups

* [WIP]

* Tag where runs are being executed

* Minor additions

* Update model with new resnet API

* [WIP] Using torchvision datasets

* Improving datasets

Leverage more and more torchvision datasets

* Reorganizing datasets

* PEP8

* No more SegmentationModel

Also remove outplanes from ResNet, and add a function for querying intermediate outputs. I won't keep it in the end, because it's very hacky and don't work with tracing

* Minor cleanups

* Moving transforms to its own file

* Move models to torchvision

* Bugfixes

* Multiply LR by 10 for classifier

* Remove classifier x 10

* Add tests for segmentation models

* Update with latest utils from classification

* Lint and missing import

* Enhance ShufflenetV2

Class shufflenetv2 receives `stages_repeats` and `stages_out_channels` arguments.

* remove explicit num_classes argument from utility functions

* Initial layout for layers with cpp extensions

* Move files around

* Fix import after move

* Add support for multiple types to ROIAlign

* Different organization

CUDA extensions work now

* Cleanups

* Reduce memory requirements for backwards

* Replace runtime_error by AT_ERROR

* Add nms test

* Add support for compilation using CPP extensions

* Change folder structure

* Add ROIPool cuda

* Cleanups

* Add roi_pool.py

* Fix lint

* Add initial structures folder for bounding boxes

* Assertion macros compatible with pytorch master (#540)

* Support for ROI Pooling (#592)

* ROI Pooling with tests. Fix for cuda context in ROI Align.

* renamed bottom and top to follow torch conventions

* remove .type().tensor() calls in favor of the new approach to tensor initialization (#626)

* Consistent naming for rois variable (#627)

* remove .type().tensor() calls in favor of the new approach to tensor initialization

* Consistent naming for rois variable in ROIPool

* ROIPool: Support for all datatypes (#632)

* Use of torch7 naming scheme for ROIAlign forward and backward

* use common cuda helpers in ROIAlign

* use .options() in favor of .type() where applicable

* Added tests for forward pass of ROIAlign, as well as more consistent naming scheme for CPU vs CUDA

* working ROIAlign cuda backwards pass

* working ROIAlign backwards pass for CPU

* added relevant headers for ROIAlign backwards

* tests for ROIAlign layer

* replace .type() with .options() for tensor initialization in ROIAlign layers

* support for Half types in ROIAlign

* gradcheck tests for ROIAlign

* updated ROIPool on CPU to work with all datatypes

* updated and cleaned tests for ROI Pooling

* Fix rebase problem

* Remove structures folder

* Improve cleanup and bugfix in test_layers

* Update C++ headers

* Add CUDAGuard to cu files

* Add more checks to layers

* Add CUDA NMS and tests

* Add multi-type support for NMS CUDA

* Avoid using THCudaMalloc

* Add clang-format and reformat c++ code

* Remove THC includes

* Rename layers to ops

* Add documentation and rename functions

* Improve the documentation a bit

* Fix some lint errors

* Fix remaining lint inssues

* Area computation doesn't add +1 in NMS

* Update CI to use PyTorch nightly

* Make NMS return indices sorted according to the score

* Address reviewer comments

* Lint fixes

* Improve doc for roi_align and roi_pool

* move to xenial

* Fix bug pointed by @lopuhin

* Fix RoIPool reference implementation in Python 2

Also fixes a bug in the clip_boxes_to_image -- this function needs a test!

* Remove change in .travis

* Minor refactoring of ShuffleNetV2

Added progress flag following #875. Further the following refactoring was also done:

1) added `version` argument in shufflenetv2 method and removed the operations for converting the `width_mult` arg to float and string.
2) removed `num_classes` argument and **kwargs from functions except `ShuffleNetV2`

* removed `version` arg

* Update shufflenetv2.py

* Removed the try except block

* Update shufflenetv2.py

* Changed version from float to str

* Replace `width_mult` with `stages_out_channels`

Removes the need of  `_getStages` function.

* remove 'input_size' parameter from shufflenetv2

* Update shufflenetv2.py

* Add ShuffleNet v2

Added 4 configurations: x0.5, x1, x1.5, x2
Add 2 pretrained models: x0.5, x1

* fix lint

* Change globalpool to torch.mean() call

* added progress flag to model getters

* flake8

* bug fix

* backward commpability

* [RFC] Add support for joint transformations in VisionDataset

* Add joints transforms for VOC and SBD

Breaking change in SBD, the xy_transform has been renamed transforms. I think this is fine given that we have not released a version of torchvision that contains it

* final changes

* final

* linter

* test changes

* linter

* lint

* indent

* lint

* minor changes

* parameter added

* ci

* ci fixes

* indent

* indent

* indent

* arg fixed

* fixed check integrity

* stylistic changes

* flake8

* added is_valid_file option

* small fixes

* fixes

* flake8 fixes

* some test

* flake8 fixes

* improvements

* modifications on tests
* fixes

* minor fix

* Add dilation option to ResNet

* Add a size check for replace_stride_with_dilation

* Fix wrong doc string

* bug fix

* Fix ResNeXt model defs with backwards compat for ResNet.

* Fix Python 2.x integer div issue

* fix inconsistent behavior for ~ expression

* remove duplicated code

* Update test_transforms.py

* Update transforms.py

* introduced new super class for all vision datasets

* Removed root from repr if dataset has no root

* reverted some overly-ambitious autoformatting

* reverted some overly-ambitious autoformatting

* added split attribute to repr of STL10 dataset

* made Python2 friendly and more robust

* Fixed call of the superclass constructor

* moved transform and target_transform back to the base classes

* added check if transforms are present before printing to avoid setting them within the constructor

* added missing transforms and target_transforms to base classes

* fixed linter error

* add aux_logits support to inception

it is related to pytorch/pytorch#18668

* instantiate InceptionAux only when requested

it is related to pytorch/pytorch#18668

* revert googlenet

* support and aux_logits in pretrained models

* return namedtuple when aux_logit is True

str.endswith can take a single string, or a tuple of strings. This replaces a loop over each extension and a call to endswith with a single call to endswith passing in all the allowed extensions. This has the advantage that the loop over each extension is done in c rather than python, and the code is a little less verbose.

* Add groups support to ResNet

* Kill BaseResNet

* Make it support multi-machine training

Making references/classification/train.py and references/classification/utils.py  compatible with python2  (#831)

* linter fixes

* linter fixes

* remove duplicate code from densenet

* correct indentation