GitLab

- RandomCrop: crop with padding using all commonly supported modes

* [WIP] functional_tensor supports more padding modes

* [WIP] Support all padding modes

* Removed wip symmetric mode

* Improvements according to the review

* [WIP] Unified Tensor/PIL crop

* Fixed misplaced type annotation

* Fixed tests
- crop with padding
- other tests using mising private functions: _is_pil_image, _get_image_size

* Unified CenterCrop and F.center_crop
- sorted includes in transforms.py
- used py3 annotations

* Unified FiveCrop and F.five_crop

* Improved tests and docs

* Unified TenCrop and F.ten_crop

* Removed useless typing in functional_pil

* Updated code according to the review
- removed useless torch.jit.export
- added missing typing return type
- fixed F.F_pil._is_pil_image -> F._is_pil_image

* Removed useless torch.jit.export

* Improved code according to the review

* [WIP] Add Tensor implementation for pad

* Unified Pad and F.pad opertion for PIL and Tensor inputs

* Added another test and improved docstring

* Updates according to the review

* Cosmetics and replaced f-string by "".format

* Updated docstring
- added compatibility support for padding as [value, ] for functional_pil.pad
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* add convert_image_dtype to functionals

* add ConvertImageDtype transform

* add test

* remove underscores from numbers since they are not compatible with python<3.6

* address review comments 1/3

* fix torch.bool

* use torch.iinfo in test

* fix flake8

* remove double conversion

* fix flake9

* bug fix

* add error messages to test

* disable torch.float16 and torch.half for now

* add docstring

* add test for consistency

* move nested function to top

* test in CI

* dirty progress

* add int to int and cleanup

* lint
Co-authored-by: Philip Meier <meier.philip@posteo.de>

* Adjust hue

* Adjust hue acceps torch.tensor uint8
Co-authored-by: Vikram Mukunda Rao Tankasali <vikramtankasali@devvm765.lla0.facebook.com>

* feat: torchscriptable adjusments

* fix: tensor output type

* feat: ColorJitter torchscriptable

* fix: too many blank lines

* fix: documentation spacing and torchscript annotation

* refactor: list type for _check_input

* refactor: reverting to original syntax
Co-authored-by: clement.joudet <clement.joudet@inventia.life>

* Make RandomHorizontalFlip torchscriptable

* Make _is_tensor_a_torch_image more generic

* Make RandomVerticalFlip torchscriptable (#2283)

* Make RandomVerticalFlip torchscriptable

* Fix lint

* Bugfix in pad

* Address review comments

* Fix lint

* Add more tests to NMS

* Fix lint

* Add norm_layer to MobileNetV2

* Add simple test case

* Small fix

* add layer freezing param to maskrcnn_resnet50_fpn

* freeze ayer param in keypointrcnn_resnet50_fpn

* layer freeze tests for mask and keypoint rcnn

* correct linting errors

* correct linting errors.

* correct linting errors

* Fix #2221, DenseNet issue with gradient checkpoints (memory_efficient=True)

* Add grad/param count test for mem_efficient densenet

* 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

* Fix for mask rcnn no detection export

* clean up

* Enable mask rcnn tests

* Added test

* update ORT

* Update .travis.yml

* fix annotation

* Clean up roi_heads

* clean up

* clean up misc ops

* Make copy of targets in GeneralizedRCNNTransform

* Fix flake8

* Adds as_tensor to functional.py

Similar functionality to to_tensor without the default conversion to float and division by 255.
Also adds support for Image mode 'L'.

* Adds tests to AsTensor()

Adds tests to AsTensor and removes the conversion to float and division by 255.

* Adds AsTensor to transforms.py

Calls the as_tensor function in functionals and adds the function AsTensor as callable from transforms.

* Removes the pic.mode == 'L'

This was handled by the else condition previously so I'll remove it.

* Fix Lint issue

Adds two line breaks between functions to fix lint issue

* Replace from_numpy with as_tensor

Removes the extra if conditionals and replaces from_numpy with as_tensor.

* Renames as_tensor to pil_to_tensor

Renames the function as_tensor to pil_to_tensor and narrows the scope of the function.  At the same time also creates a flag that defaults to True for swapping to the channels first format.

* Renames AsTensor to PILToImage

Renames the function AsTensor to PILToImage and modifies the description.  Adds the swap_to_channelsfirst boolean variable to indicate if the user wishes to change the shape of the input.

* Add the __init__ function to PILToTensor 

Add the __init__ function to PILToTensor since it contains the swap_to_channelsfirst parameter now.

* fix lint issue

remove trailing white space

* Fix the tests

Reflects the name change to PILToTensor and the parameter to the function as well as the new narrowed scope that the function only accepts PIL images.

* fix tests

Instead of undoing the transpose just create a new tensor and test that one.

* Add the view back

Add img.view(pic.size[1], pic.size[0], len(pic.getbands())) back to outside the if condition.

* fix test

fix conversion from torch tensor to PIL back to torch tensor.

* fix lint issues

* fix lint

remove trailing white space

* Fixed the channel swapping tensor test

Torch tranpose operates differently than numpy transpose.  Changed operation to permute.

* Add mode='F'

Add mode information when converting to PIL Image from Float Tensor.

* Added inline comments to follow shape changes

* ToPILImage converts FloatTensors to uint8

* Remove testing not swapping

* Removes the swap_channelsfirst parameter

Makes the channel swapping the default behavior.

* Remove the swap_channelsfirst argument

Remove the swap_channelsfirst argument and makes the swapping the default functionality.

* 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

* Check target boxes input on generalized_rcnn.py

* Fix target box validation in generalized_rcnn.py

* Add tests for input validation of detection models

* 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

* 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

* Fix missing compilation files for video-reader

* Disable IO tests in travis

* 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

* only display extensions if available

* add tests

* fix lint

* 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>

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

* Fix lint

* improve stability of test_nms_cuda

This change addresses two issues:

_create_tensors_with_iou() creates test data for the NMS tests. It
takes care to ensure at least one pair of boxes (1st and last) have
IoU around the threshold for the test. However, the constructed
IoU for that pair is _so_ close to the threshold that rounding
differences (presumably) between CPU and CUDA implementations may
result in one suppressing a box in the pair and the other not.
Adjust the construction to ensure the IoU for the box pair is
near the threshold, but far-enough above that both implementations
should agree.

Where 2 boxes have nearly or exactly the same score, the CPU and
CUDA implementations may order them differently. Adjust
test_nms_cuda() to check only that the non-suppressed box lists
include the same members, without regard for ordering.

* adjust assertion in test_nms_cuda

The CPU and CUDA nms implementations each sort the box scores
as part of their work, but the sorts they use are not stable. So
boxes with the same score maybe be processed in opposite order
by the two implmentations.

Relax the assertion in test_nms_cuda (following the model in
pytorch's test_topk()) to allow the test to pass if the output
differences are caused by similarly-scored boxes.

* improve stability of test_nms_cuda

Adjust _create_tensors_with_iou() to ensure we create at least
one box just over threshold that should be suppressed.

* Add CircleCI job for python lint

* Break lint

* Fix

* Fix lint

* Re-enable all tests and remove travis python lint

* Add test for large batches in DeformConv2d

* Clean-up and (try) fix DeformConv2d

* Simplifications and bugfixes

* Try fix CUDA now

* fixes and tests for variable input size

* transform test fix

* Fix comment

* Dynamic shape for keypoint_rcnn

* Update test_onnx.py

* Update rpn.py

* Fix for split on RPN

* Fixes for feedbacks

* flake8

* topk fix

* Fix build

* branch on tracing

* fix for scalar tensor

* Fixes for script type annotations

* Update rpn.py

* clean up

* clean up

* Update rpn.py

* Updated for feedback

* Fix for comments

* revert to use tensor

* Added test for box clip

* Fixes for feedback

* Fix for feedback

* ORT version revert

* Update ort

* Update .travis.yml

* Update test_onnx.py

* Update test_onnx.py

* Tensor sizes

* Fix for dynamic split

* Try disable tests

* pytest verbose

* revert one test

* enable tests

* Update .travis.yml

* Update .travis.yml

* Update .travis.yml

* Update test_onnx.py

* Update .travis.yml

* Passing device

* Fixes for test

* Fix for boxes datatype

* clean up
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>