GitLab

* Overwriting FrozenBN eps=0.0 if pretrained=True for detection models.

* Moving the method to detection utils and adding comments.

* style: Added annotation typing for vgg

* fix: Fixed annotation typing

* refactor: Removed un-necessary import

* fix: Added missing annotation for kwargs

* fix: Fixed constructor typing

* refactor: Refactored typing to minize changes

* refactor: Refactored typing cast

* fix: Fixed module list typing

* fix: Fixed constructor typing in models._utils

* fix: Fixed constructor typing in models.alexnet

* fix: Fixed constructor typing in models.mnasnet

* fix: Fixed constructor typing in models.squeezenet

* style: Added annotation typing for mmobilenet

* fix: Fixed type hinting of adaptive pooling

* refactor: Removed un-necessary import

* fix: Fixed constructor typing

* fix: Fixed list typing

* style: Added annotation typing for googlenet

* fix: Removed duplicate typing

* refactor: Moved factory function after class definition to fix typing

* fix: Fixed annotation typing

* refactor: Removed un-necessary import

* fix: Fixed typing

* refactor: Moved back up helper function and quote typed it

* style: Added annotation typing for inception

* refactor: Moved factory function after class definition

* style: Changed attribute setting for type hinting

* refactor: Removed un-necessary import

* fix: Fixed typing in constructors

* fix: Fixed kwargs typing

* style: Fixed lint

* refactor: Moved helpers function back and quote typed it

* style: Added annotation typing for resnet

* fix: Fixed annotation to pass classes

* fix: Fixed annotation typing

* fix: Fixed annotation typing

* fix: Fixed annotation typing for resnet

* refactor: Removed un-necessary import

* fix: Fixed constructor typing

* style: Added black formatting on _resnet

* style: Added annotation typing for squeezenet

* feat: Added typing for kwargs

* style: Added annotation typing for mnasnet

* refactor: Removed un-necessary import

* style: Added typing in models._utils

* fix: Removed non-necessary import

* fix: Removed type annotation of forward method

* refactor: Removed un-necessary import

* Vectorize operations, across all feaure levels.

* Remove unnecessary other_outputs variable.

* Split per feature level.

* Perform batched_nms across feature levels.

* Add extra parameter for limiting detections before and after nms.

* Restoring default threshold.

* Apply suggestions from code review
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Renaming variable.
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Add rough implementation of RetinaNet.

* Move AnchorGenerator to a seperate file.

* Move box similarity to Matcher.

* Expose extra blocks in FPN.

* Expose retinanet in __init__.py.

* Use P6 and P7 in FPN for retinanet.

* Use parameters from retinanet for anchor generation.

* General fixes for retinanet model.

* Implement loss for retinanet heads.

* Output reshaped outputs from retinanet heads.

* Add postprocessing of detections.

* Small fixes.

* Remove unused argument.

* Remove python2 invocation of super.

* Add postprocessing for additional outputs.

* Add missing import of ImageList.

* Remove redundant import.

* Simplify class correction.

* Fix pylint warnings.

* Remove the label adjustment for background class.

* Set default score threshold to 0.05.

* Add weight initialization for regression layer.

* Allow training on images with no annotations.

* Use smooth_l1_loss with beta value.

* Add more typehints for TorchScript conversions.

* Fix linting issues.

* Fix type hints in postprocess_detections.

* Fix type annotations for TorchScript.

* Fix inconsistency with matched_idxs.

* Add retinanet model test.

* Add missing JIT annotations.

* Remove redundant model construction

Make tests pass

* Fix bugs during training on newer PyTorch and unused params in DDP

Needs cleanup and to add back support for images with no annotations

* Cleanup resnet_fpn_backbone

* Use L1 loss for regression

Gives 1mAP improvement over smooth l1

* Disable support for images with no annotations

Need to fix distributed first

* Fix retinanet tests

Need to deduplicate those box checks

* Fix Lint

* Add pretrained model

* Add training info for retinanet
Co-authored-by: Hans Gaiser <hansg91@gmail.com>
Co-authored-by: Hans Gaiser <hans.gaiser@robovalley.com>
Co-authored-by: Hans Gaiser <hans.gaiser@robohouse.com>

Co-authored-by: vfdev <vfdev.5@gmail.com>

Change the default anchor generator settings to default Faster RCNN version(without FPN), so it is hopefully less misleading. Also add an assert to grad_anchors functions to make sure people use it as it is aspected.

* Readme for video models.

* Adressing @fmassa comments
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

Replace nonzero by where, now that it works with just a condition

* partially enable mypy for .models

* fix existing errors

* ignore error instead of using Union

* fix type hints and move degenerate boxes to a function in torchvision.models.detection.generalized_rcnn

* format code

* format code

* changed to static method

* revert imports

* changed to method

* revert procedure for degenerating boxes

* Update transform.py

* Update transform.py

* Try remove eager scripting calls

* remove script call
Co-authored-by: eellison <eellison@fb.com>
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Remove interpolate in favor of PyTorch's implementation

* Bugfix

* Bugfix

* Add norm_layer to MobileNetV2

* Add simple test case

* Small fix

Co-authored-by: eellison <eellison@fb.com>

* 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

Another instance of integer division using the division operator. In this case line 266 already shows the correct formulation, so line 185 only needs the update.

Integer division using the div operator is deprecated and will throw a RuntimeError in PyTorch 1.6 (and on PyTorch Master very soon). Running a test build with a recent Torchvision commit and integer division using div ('/') disabled revealed this integer division. 

I'll re-run the tests once this is fixed in case it's masking additional issues.

* Make copy of targets in GeneralizedRCNNTransform

* Fix flake8

Co-authored-by: eellison <eellison@fb.com>