GitLab

Rewrite draw_segmentation_masks and update gallery example to illustrate both instance and semantic segmentation models (#3824)

* Added support for bicubic mode with AA

* Updated comment in the test

* Partial implementation of SSDlite.

* Add normal init and BN hyperparams.

* Refactor to keep JIT happy

* Completed SSDlite.

* Fix lint

* Update todos

* Add expected file in repo.

* Use C4 expansion instead of C4 output.

* Change scales formula for Default Boxes.

* Add cosine annealing on trainer.

* Make T_max count epochs.

* Fix test and handle corner-case.

* Add support of support width_mult

* Add ssdlite presets.

* Change ReLU6, [-1,1] rescaling, backbone init & no pretraining.

* Use _reduced_tail=True.

* Add sync BN support.

* Adding the best config along with its weights and documentation.

* Make mean/std configurable.

* Fix not implemented for half exception

Co-authored-by: James Thewlis <james@unitary.ai>

* hello

* Try with DYLD_FALLBACK_LIBRARY_PATH
Co-authored-by: Edgar Andrés Margffoy Tuay <andfoy@gmail.com>

* WIP Added antialias option to transforms.functional.resize

* Updates according to the review

* Excluded these C++ files for iOS build

* Added support for mixed downsampling/upsampling

* Fixed heap overflow caused by explicit loop unrolling

* Applied PR review suggestions
- used pytest parametrize instead unittest
- cast to scalar_t ptr
- removed interpolate aa files for ios/android keeping original cmake version

* Early skeleton of API.

* Adding MultiFeatureMap and vgg16 backbone.

* Making vgg16 backbone same as paper.

* Making code generic to support all vggs.

* Moving vgg's extra layers a separate class + L2 scaling.

* Adding header vgg layers.

* Fix maxpool patching.

* Refactoring code to allow for support of different backbones & sizes:
- Skeleton for Default Boxes generator class
- Dynamic estimation of configuration when possible
- Addition of types

* Complete the implementation of DefaultBox generator.

* Replace randn with empty.

* Minor refactoring

* Making clamping between 0 and 1 optional.

* Change xywh to xyxy encoding.

* Adding parameters and reusing objects in constructor.

* Temporarily inherit from Retina to avoid dup code.

* Implement forward methods + temp workarounds to inherit from retina.

* Inherit more methods from retinanet.

* Fix type error.

* Add Regression loss.

* Fixing JIT issues.

* Change JIT workaround to minimize new code.

* Fixing initialization bug.

* Add classification loss.

* Update todos.

* Add weight loading support.

* Support SSD512.

* Change kernel_size to get output size 1x1

* Add xavier init and refactoring.

* Adding unit-tests and fixing JIT issues.

* Add a test for dbox generator.

* Remove unnecessary import.

* Workaround on GeneralizedRCNNTransform to support fixed size input.

* Remove unnecessary random calls from the test.

* Remove more rand calls from the test.

* change mapping and handling of empty labels

* Fix JIT warnings.

* Speed up loss.

* Convert 0-1 dboxes to original size.

* Fix warning.

* Fix tests.

* Update comments.

* Fixing minor bugs.

* Introduce a custom DBoxMatcher.

* Minor refactoring

* Move extra layer definition inside feature extractor.

* handle no bias on init.

* Remove fixed image size limitation

* Change initialization values for bias of classification head.

* Refactoring and update test file.

* Adding ResNet backbone.

* Minor refactoring.

* Remove inheritance of retina and general refactoring.

* SSD should fix the input size.

* Fixing messages and comments.

* Silently ignoring exception if test-only.

* Update comments.

* Update regression loss.

* Restore Xavier init everywhere, update the negative sampling method, change the clipping approach.

* Fixing tests.

* Refactor to move the losses from the Head to the SSD.

* Removing resnet50 ssd version.

* Adding support for best performing backbone and its config.

* Refactor and clean up the API.

* Fix lint

* Update todos and comments.

* Adding RandomHorizontalFlip and RandomIoUCrop transforms.

* Adding necessary checks to our tranforms.

* Adding RandomZoomOut.

* Adding RandomPhotometricDistort.

* Moving Detection transforms to references.

* Update presets

* fix lint

* leave compose and object

* Adding scaling for completeness.

* Adding params in the repr

* Remove unnecessary import.

* minor refactoring

* Remove unnecessary call.

* Give better names to DBox* classes

* Port num_anchors estimation in generator

* Remove rescaling and fix presets

* Add the ability to pass a custom head and refactoring.

* fix lint

* Fix unit-test

* Update todos.

* Change mean values.

* Change the default parameter of SSD to train the full VGG16 and remove the catch of exception for eval only.

* Adding documentation

* Adding weights and updating readmes.

* Update the model weights with a more performing model.

* Adding doc for head.

* Restore import.

Summary:
Pull Request resolved: https://github.com/pytorch/vision/pull/3748

This PR parametrizes the `perspective`-related tests, and avoids having deeply nested for-loops which will help debugging. "What" gets tested is left unchanged.

The newly-introduced `cpu_and_gpu()` generator along with the `dont_collect` mark is a logic that allows to not run CPU tests on GPU machines (and vice versa).

Reviewed By: fmassa

Differential Revision: D27908299

fbshipit-source-id: 24a10a89fe90ae0a9e62de4bc7e768a669ebf212

Revert "Revert "Ported places365 dataset's tests to the new test framework (#3705)" (#3718)" (#3731)

This reverts commit d4195587.

This reverts commit 4b0b332a.

* Ported places365 dataset's tests to the new test framework

* Made some attributes private

* Removed unnecessary compute_md5()

* Added test_images_download_preexisting()
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

* refactor test_models to use pytest

* Also xfail the detection models

* Remove xfail and just comment out expected failing parts

* Comment out some more

* put back commented checks

* cleaning + comment

* docs

* void unnecessary changes

* r2plus1d_18 seems  to segfault on linux gpu??

* put back test, failure is unrelated
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* fix test

* more robust test

* flake8
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* Ported STL10 dataset's tests to new test framework

* Added additional tests

* Removed unused import

* Made private methods static and other minor changes

* Ported SVHN dataset to new test framework

* Fixed flake8 error and added REQUIRED_PACKAGES=scipy

* Remove pandas dependecy for CelebA dataset

* address PR comments

* Apply suggestions from code review
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Added KITTI dataset

* Addressed review comments

* Changed type of target to List[Dict] and corrected the data types of the returned values.

* Updated unit test to rely on ImageDatasetTestCase

* Added kitti to dataset documentation

* Cleaned up test and some minor changes

* Made data_url a string instead of a list

* Removed unnecessary try and print
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* WIP

* clang

* docs

* extracted out common utils

* Use better quantization function and pass tensors as parameters

* proper dequantization

* Some tests

* Dequantization optimization, seems to gain a few ms

* clang-format

* again

* more correct test. Had to remove optimization although it almost works

* Also test aligned=True

* remove useless part

* more docs and comments

* Put back optimization with more robust test

* Added check for index upper bound

* avoid possible overflow

* Move common function into common.h

* oops

* scale=1,zero_point=0 makes more sense

* Force batch size of 1 to prevent any indexingbug

* format

* format again

* updated docstring

* put back description comment for pre_calc_bilinear_interpolate

* revert most changes to docstring as it's taken care of in another PR

* new image

* avoid check if pil version is < 8.2 as the reference image would be different

* start adding tests

* add return type and doc

* adds tests

* add no fill tests

* add rgb test

* check inplace

* bug fix

* bug fix

* rewrite make grid

* add plotting demos

* rename file

* remove

* updt

* Add viz

* updt

* update readme, add links

* complte bounding boxes

* Complete the examples!

* link fix

* link fixed
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

* add tests for (Dataset|Image)Folder

* lint

* remove old tests

* cleanup

* more cleanup

* adapt tests

* fix make_dataset

* remove powerset

* readd import

Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Add quantized version of nms

* Added tests

* Compute areas only once

* remove calls to dequantize_val

* fix return type for empty tensor

* flake8

* remove use of scale as it gets cancelled out

* simpler int convertion in tests

* explicitly set ovr to double

* add tests for more values of scale and zero_point

* comment about underflow

* remove unnecessary accessor

* properly convert to float for division

* Add comments about underflow

* explicitely cast coordinates to float to allow vectorization

* clang

* clang  again

* hopefully OK now