GitLab

* Simplify the ACCEPT=True logic in assertExpected().

* Separate the expected filename estimation from assertExpected

* Unflatten expected values.

* Assert for duplicate scores if primary check fails.

* Remove custom exceptions for algorithms and add a compact function for shrinking large ouputs.

* Removing unused variables.

* Add warning and comments.

* Re-enable all autocast unit-test for detection and marking the tests as skipped in partial validation.

* Move test skip at the end.

* Changing the warning message.

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

* Moving the method to detection utils and adding comments.

* Change default eps value of FrozenBN.

* Update the unit-tests.`

* Update the expected values.

* Revert the expected value and use original eps=0 value for flaky tests.

* Post init change of eps.

* Styles.

* Modify expected value and threshold for retinanet unit-test.

* Disable tests on GPU
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Fixes Xiao's repro

* Ports nms to use full dispatcher

* Move HIPGuard to nms_cuda

* clang-format

* run models in test_models.py on GPU if available

* Francisco's comment, also disable cuda model tests to see if CPU alone still passes

* cuda tests now pass locally, although still not comparing to saved numerics

* add note for thing to ask francisco

* Allow cuda and cpu tests to share a data file

* ignore suffix if unneeded

* Skip autocast numerics checks for a few models

* Add roi_align test
Co-authored-by: Michael Carilli <mcarilli@nvidia.com>

* Add norm_layer to MobileNetV2

* Add simple test case

* Small fix

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

* Add grad/param count test for mem_efficient densenet

* 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 googlenet no aux logits

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

* feat: Added __repr__ attribute to GeneralizedRCNNTransform

Added more details to default __repr__ attribute for printing.

* fix: Put back relative imports

* style: Fixed pep8 compliance

Switched strings with  syntax to f-strings.

* test: Added test for GeneralizedRCNNTransform __repr__

Checked integrity of __repr__ attribute

* test: Fixed unittest for __repr__

Fixed the formatted strings in the __repr__ integrity check for GeneralizedRCNNTransform

* fix: Fixed f-strings for earlier python versions

Switched back f-strings to .format syntax for Python3.5 compatibility.

* fix: Fixed multi-line string

Fixed multiple-line string syntax for compatibility

* fix: Fixed GeneralizedRCNNTransform unittest

Fixed formatting of min_size argument of the resizing part

* Fix AnchorGenerator if moving from one device to another

* Fixes for the test

* Add tests for results in script vs eager mode

This copies some logic from `test_jit.py` to check that a TorchScript'ed
model's outputs are the same as outputs from the model in eager mode.

To support differences in TorchScript / eager mode outputs, an
`unwrapper` function can be provided per-model.

* Fix inception, use PYTORCH_TEST_WITH_SLOW

* Update

* Remove assertNestedTensorObjectsEqual

* Add PYTORCH_TEST_WITH_SLOW to CircleCI config

* Add MaskRCNN unwrapper

* fix prec args

* Remove CI changes

* update

* Update

* remove expect changes

* Fix tolerance bug

* Fix breakages

* Fix quantized resnet

* Fix merge errors and simplify code

* DeepLabV3 has been fixed

* Temporarily disable jit compilation

* almost working...

* respond to comments

* add empty tensor op, handle different output types in generalized rcnn

* clean ups

* address comments

* more changes

* it's working!

* torchscript bugs

* add script/ eager test

* eval script model

* fix flake

* division import

* py2 compat

* update test, fix arange bug

* import division statement

* fix linter

* fixes

* changes needed for JIT master

* cleanups

* remove imagelist_to

* requested changes

* Make FPN backwards-compatible and torchscript compatible

We remove support for feature channels=0, but support for it was already a bit limited

* Fix ONNX regression

* correctness test implemented with old test architecture

* reverted an unneeded change, ran flake8

* moving to relative tolerance of 1 part in 10k for classification correctness checks

* going down to 1 part in 1000 for correctness checks bc architecture differences

* one percent relative tolerance

This reverts commit 1e857d93.

* added correctness tests for classification models
* refactored tests for extensibility & usability
* flake8 fixes

* add support for video resnet models, restructure script test to just ignore RCNN models

* switch back to testing subset of the models

* add expected result tests

* fix wrong assertion

* start with only detection models

* remove unneeded rng setting

* fix test

* add tuple support

* update test

* syntax error

* treat .pkl files as binary data, see : https://git-scm.com/book/en/v2/Customizing-Git-Git-Attributes#_binary_files

* fix test

* fix elif

* Map tensor results and enforce maximum pickle size

* unrelated change

* larger rtol

* pass rtol atol around

* last commit i swear...

* respond to comments

* fix flake

* fix py2 flake

* make googlnet scriptable

* Remove typing import in favor of torch.jit.annotations

* add inceptionnet

* flake fixes

* fix asssert true

* add import division for torchscript

* fix script compilation

* fix flake, py2 division error

* fix py2 division error

* script_fcn_resnet

* Make old models load

* DeepLabV3 also got torchscript-ready

* make densenet scriptable

* make py2 compat

* use torch List polyfill

* fix unpacking for checkpointing

* fewer changes to _Denseblock

* improve error message

* print traceback

* add typing dependency

* add typing dependency to travis too

* Make loading old checkpoints work

* Make AnchorGenerator support half precision

* Add test for fasterrcnn with double

* convert gt_boxes to right dtype

* make shufflenet scriptable

* make resnet18 scriptable

* set downsample to identity instead of __constants__ api

* use __constants__ for downsample instead of identity

* import tensor to fix flake

* use torch.Tensor type annotation instead of import

* test that torchhub models are scriptable

* fix lint

* [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

* [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

* 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

* 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

* [Remove] Use stride in 1x1 in resnet

This is temporary

* Move files to torchvision

Inference works

* Now seems to give same results

Was using the wrong number of total iterations in the end...

* Distributed evaluation seems to work

* Factor out transforms into its own file

* Enabling horizontal flips

* MultiStepLR and preparing for launches

* Add warmup

* Clip gt boxes to images

Seems to be crucial to avoid divergence. Also reduces the losses over different processes for better logging

* Single-GPU batch-size 1 of CocoEvaluator works

* Multi-GPU CocoEvaluator works

Gives the exact same results as the other one, and also supports batch size > 1

* Silence prints from pycocotools

* Commenting unneeded code for run

* Fixes

* Improvements and cleanups

* Remove scales from Pooler

It was not a free parameter, and depended only on the feature map dimensions

* Cleanups

* More cleanups

* Add misc ops and totally remove maskrcnn_benchmark

* nit

* Move Pooler to ops

* Make FPN slightly more generic

* Minor improvements or FPN

* Move FPN to ops

* Move functions to utils

* Lint fixes

* More lint

* Minor cleanups

* Add FasterRCNN

* Remove modifications to resnet

* Fixes for Python2

* More lint fixes

* Add aspect ratio grouping

* Move functions around

* Make evaluation use all images for mAP, even those without annotations

* Bugfix with DDP introduced in last commit

* [Check] Remove category mapping

* Lint

* Make GroupedBatchSampler prioritize largest clusters in the end of iteration

* Bugfix for selecting the iou_types during evaluation

Also switch to using the torchvision normalization now on, given that we are using torchvision base models

* More lint

* Add barrier after init_process_group

Better be safe than sorry

* Make evaluation only use one CPU thread per process

When doing multi-gpu evaluation, paste_masks_in_image is multithreaded and throttles evaluation altogether. Also change default for aspect ratio group to match Detectron

* Fix bug in GroupedBatchSampler

After the first epoch, the number of batch elements could be larger than batch_size, because they got accumulated from the previous iteration. Fix this and also rename some variables for more clarity

* Start adding KeypointRCNN

Currently runs and perform inference, need to do full training

* Remove use of opencv in keypoint inference

PyTorch 1.1 adds support for bicubic interpolation which matches opencv (except for empty boxes, where one of the dimensions is 1, but that's fine)

* Remove Masker

Towards having mask postprocessing done inside the model

* Bugfixes in previous change plus cleanups

* Preparing to run keypoint training

* Zero initialize bias for mask heads

* Minor improvements on print

* Towards moving resize to model

Also remove class mapping specific to COCO

* Remove zero init in bias for mask head

Checking if it decreased accuracy

* [CHECK] See if this change brings back expected accuracy

* Cleanups on model and training script

* Remove BatchCollator

* Some cleanups in coco_eval

* Move postprocess to transform

* Revert back scaling and start adding conversion to coco api

The scaling didn't seem to matter

* Use decorator instead of context manager in evaluate

* Move training and evaluation functions to a separate file

Also adds support for obtaining a coco API object from our dataset

* Remove unused code

* Update location of lr_scheduler

Its behavior has changed in PyTorch 1.1

* Remove debug code

* Typo

* Bugfix

* Move image normalization to model

* Remove legacy tensor constructors

Also move away from Int and instead use int64

* Bugfix in MultiscaleRoiAlign

* Move transforms to its own file

* Add missing file

* Lint

* More lint

* Add some basic test for detection models

* More lint

* 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

* Add dilation option to ResNet

* Add a size check for replace_stride_with_dilation

* Add test for loading pretrained models

The update modifies the test to check whether the model can successfully load the pretrained weights. Will raise an error if the model parameters are incorrectly defined or named.

* Add test on 'num_class'

Passing num_class equal to a number other than 1000 helps in making the test more enforcing in nature.

* Add basic model testing.

Also fixes flaky test

* Fix flake8