GitLab

As requested by @fmassa in comment
https://github.com/pytorch/vision/issues/2216#issuecomment-630166106
from #2216.

* Fix missing include for OSX in video decoder

* clang-format

* freeze layers only if pretrained backbone is used

If pretrained backbone is not used and one intends to train the entire network from scratch, no layers should be frozen.

* function argument to control the trainable features

Depending on the size of dataset one might want to control the number of tunable parameters in the backbone, and this parameter in hyper parameter optimization for the dataset. It would be nice to have this function support this.

* ensuring tunable layer argument is valid

* backbone freezing in fasterrcnn_resnet50_fpn

Handle backbone freezing in fasterrcnn_resnet50_fpn function rather than the resnet_fpn_backbone function that it uses to get the backbone.

* remove layer freezing code

layer freezing code has been moved to fasterrcnn_resnet50_fpn function that consumes resnet_fpn_backbone function.

* correcting linting errors

* correcting linting errors

* move freezing logic to resnet_fpn_backbone

Moved layer freezing logic to resnet_fpn_backbone with an additional parameter.

* remove layer freezing from fasterrcnn_resnet50_fpn

Layer freezing logic has been moved to resnet_fpn_backbone. This function only ensures that the all layers are made trainable if pretrained models are not used.

* update example resnet_fpn_backbone docs

* correct typo in var name

* correct indentation

* adding test case for layer freezing in faster rcnn

This PR adds functionality to specify the number of trainable layers while initializing the faster rcnn using fasterrcnn_resnet50_fpn function. This commits adds a test case to test this functionality.

* updating layer freezing condition for clarity

More information in PR

* remove linting errors

* removing linting errors

* removing linting errors

Fixes https://github.com/pytorch/vision/issues/2214#issuecomment-628636663

I don't know why the building is not working with `--expt-relaxed-constexpr` flag set, but it is generally a good idea to declare this as `__host__ __device__`

* Check target boxes input on generalized_rcnn.py

* Fix target box validation in generalized_rcnn.py

* Add tests for input validation of detection models

Fix https://github.com/pytorch/vision/issues/2193.

* feat: Added eps argument to FrozenBatchNorm2d

* test: Added unittest for eps addition in FrozenBatchNorm2d

See #2169

* fix: Reverted forward changes for JIT fuser

* fix: Added back n argument for backward-compatibility

* fix: Fixed FrozenBatchNorm2d forward

Added back eps

* feat: Specified deprecation warnings in FrozenBatchNorm2d

* test: Added unittest for deprecation warninig in FrozenBatchNorm2d

* style: Fixed lint

* style: Fixed block comment lint

* feat: Restored support of tuple of Tensors for roi_align & roi_pool

* test: Added unittest for Tensor sequence support by region pooling

* test: Fixed typo in unittest

* test: Fixed data type

* test: Fixed roi pooling tensor unittest

* test: Fixed box format conversion

* add mypy config

* fix syntax error

* fix annotations in torchvision/utils.py

* add mypy type check to CircleCI

* add mypy cache to ignore files

* try fix CI

* ignore flake8 F821 since it interferes with mypy

* add mypy type check to config generator

* explicitly set config files

* Fix mypy type annotations

* follow torchscript Tuple type

* redefine torch_choice output type

* change the type in cached_grid_anchors

* minor bug
Co-authored-by: Guanheng Zhang <zhangguanheng@devfair0197.h2.fair>
Co-authored-by: Guanheng Zhang <zhangguanheng@learnfair0341.h2.fair>

* Fixing nms on boxes when no detection

* test

* Fix for scale_factor computation

* remove newline

* Fix for mask_rcnn dynanmic axes

* Clean up

* Update transform.py

* Fix for torchscript

* Fix scripting errors

* Fix annotation

* Fix lint

* Fix annotation

* Fix for interpolate scripting

* Fix for scripting

* refactoring

* refactor the code

* Fix annotation

* Fixed annotations

* Added test for resize

* lint

* format

* bump ORT

* ort-nightly version

* Going to ort 1.1.0

* remove version

* install typing-extension

* Export model for images with no detection

* Upgrade ort nightly

* update ORT

* Update test_onnx.py

* updated tests

* Updated tests

* merge

* Update transforms.py

* Update cityscapes.py

* Update celeba.py

* Update caltech.py

* Update pkg_helpers.bash

* Clean up

* Clean up for dynamic split

* Remove extra casts

* flake8

Now the dataset is not working properly because of this line of code `indices = [i for i in range(len(video_list)) if video_list[i][len(self.root) + 1:] in selected_files]`. 
Performing the `len(self.root) + 1` only make sense if there is no training / to root

```
>>> root = 'data/ucf-101/videos'
>>> video_path = 'data/ucf-101/videos/activity/video.avi'
>>> video_path [len(root ):]
'/activity/video.avi'
>>> video_path [len(root ) + 1:]
'activity/video.avi'
```

Appending the root path also to the selected files is a simple solution and make the dataset works with and without a trailing slash.

* feat: Added number of features in FrozenBatchNorm2d repr

While BatchNorm layers have extensive information in their repr, FrozenBatchNorm2d has one

* refactor: Refactored FrozenBatchNorm2d __repr__

* test: Added unittest for FrozenBatchNorm2d __repr__

* style: Removed blank lines in test_ops

* refactor: Avoids creating an extra attribute for __repr__

* style: Switched __repr__ to f-string

Since support of Python version ealier than 3.6 have been dropped, f-string can be used.

* fix: Fixed typo in __repr__

* style: Switched unittest .format to f-string

`Mn`, `Sn` are used as mean and std, but their suddenly turned to be
`mean[n]` and `std[n]` in about 10 words later

At the moment in the ASPP-Layer the number of output channels are predefined as a constant,
which is good for DeepLab but not necessairly in other projects, where another out-channel Nr. is required.

Also the number of "atrous rates" is fixed to three, which also could be sometimes more or less depending on the notwork-arch.
Again these fixed values may make sense in DeepLab-Model but not necessarily in other type of models.

This pull-req. contains the needed changes to make ASPP-Layer generic.

* Don't include CUDAApplyUtils.cuh

* fix format

* fix atomic

* Improve documentation for NMS

* update nms doc for special case

* only display extensions if available

* add tests

* fix lint

* For detection model, replace L1 loss with beta smooth L1 loss to achieve better performance.

* Add type annotations for torchscript

* Resolve E226

* fix the use of contiguous() in kernels

* clang-format

* add a contiguous in nms
Co-authored-by: Yuxin Wu <ppwwyyxx@users.noreply.github.com>

* Fixing nms on boxes when no detection

* test

* Fix for scale_factor computation

* remove newline

* Fix for mask_rcnn dynanmic axes

* Clean up

* Update transform.py

* Fix for torchscript

* Fix scripting errors

* Fix annotation

* Fix lint

* Fix annotation

* Fix for interpolate scripting

* Fix for scripting

* refactoring

* refactor the code

* Fix annotation

* Fixed annotations

* Added test for resize

* lint

* format

* bump ORT

* ort-nightly version

* Going to ort 1.1.0

* remove version

* install typing-extension

Summary:
Pull Request resolved: https://github.com/pytorch/vision/pull/2077

Pull Request resolved: https://github.com/facebookresearch/SlowFast/pull/164

This is a follow-up diff from D18720474

We will be releasing a new version of torchvision soon and the signature of those functions is not ready yet, following my comment in https://our.intern.facebook.com/intern/diff/D18720474/?transaction_id=561239541337402



Reviewed By: stephenyan1231

Differential Revision: D20914571

fbshipit-source-id: 1a7560b8f8e46ab42ef376c50b494a4f73923e94
Co-authored-by: Francisco Massa <fmassa@fb.com>

Torchvision includes at least 3 bits of code that calculate
box Intersection over Union values (and usually compare to
a threshold):

- box_iou in torchvision/ops/boxes.py
- devIoU in torchvision/csrc/cuda/nms_cuda.cu
- nms_cpu_kernel in torchvision/csrc/cpu/nms_cpu.cpp

The calculations were performed slightly differently between
those, leading to occasional differences in results.

Update devIoU to use the same method as the others for better
consistency.

This change improves agreement between the CPU and CUDA
calculations but the results can still differ slightly.
Setting NVCC_FLAGS to include "--fmad=true" would provide
still better agreement, but with likely cost to performance.

* Add tests for negative samples for Mask R-CNN and Keypoint R-CNN

* Fix lint