- 25 Jan, 2022 1 commit
-
-
Piyush Singh authored
* replace assert with valueerror * pytest should raise ValueError not AssertionError * minor edit * raise assert changed to raise valueerror in test * Update torchvision/models/detection/backbone_utils.py Co-authored-by:
Aditya Oke <47158509+oke-aditya@users.noreply.github.com> * Update torchvision/models/detection/backbone_utils.py Co-authored-by:
Abhijit Deo <72816663+abhi-glitchhg@users.noreply.github.com> Co-authored-by:
Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
- 21 Jan, 2022 1 commit
-
-
Hu Ye authored
* add fcos * update fcos * add giou_loss * add BoxLinearCoder for FCOS * add full code for FCOS * add giou loss * add fcos * add __all__ * Fixing lint * Fixing lint in giou_loss.py * Add typing annotation to fcos * Add trained checkpoints * Use partial to replace lambda * Minor fixes to docstrings * Apply ufmt format * Fixing docstrings * Fixing jit scripting * Minor fixes to docstrings * Fixing jit scripting * Ignore mypy in fcos * Fixing trained checkpoints * Fixing unit-test of jit script * Fixing docstrings * Add test/expect/ModelTester.test_fcos_resnet50_fpn_expect.pkl * Fixing test_detection_model_trainable_backbone_layers * Update test_fcos_resnet50_fpn_expect.pkl * rename stride to box size * remove TODO and fix some typo * merge some code for better * impove the comments * remove decode and encode of BoxLinearCoder * remove some unnecessary hints * use the default value in detectron2. * update doc * Add unittest for BoxLinearCoder * Add types in FCOS * Add docstring for BoxLinearCoder * Minor fix for the docstring * update doc * Update fcos_resnet50_fpn_coco pretained weights url * Update torchvision/models/detection/fcos.py Co-authored-by:
Zhiqiang Wang <zhiqwang@foxmail.com> * Update torchvision/prototype/models/detection/fcos.py Co-authored-by:
Joao Gomes <jdsgomes@fb.com> Co-authored-by:
Joao Gomes <joaopsgomes@gmail.com>
-
- 04 Oct, 2021 1 commit
-
-
Philip Meier authored
* add ufmt as code formatter * cleanup * quote ufmt requirement * split imports into more groups * regenerate circleci config * fix CI * clarify local testing utils section * use ufmt pre-commit hook * split relative imports into local category * Revert "split relative imports into local category" This reverts commit f2e224cde2008c56c9347c1f69746d39065cdd51. * pin black and usort dependencies * fix local test utils detection * fix ufmt rev * add reference utils to local category * fix usort config * remove custom categories sorting * Run pre-commit without fixing flake8 * got a double import in merge Co-authored-by:Nicolas Hug <nicolashug@fb.com>
-
- 14 Jul, 2021 1 commit
-
-
Philip Meier authored
Co-authored-by:
-
- 10 Jun, 2021 1 commit
-
-
Anirudh authored
-
- 21 May, 2021 1 commit
-
-
Nicolas Hug authored
Co-authored-by:Philip Meier <github.pmeier@posteo.de>
-
- 20 Jan, 2021 1 commit
-
-
Alessio Falai authored
Co-authored-by:
-
- 18 Jan, 2021 1 commit
-
-
Vasilis Vryniotis authored
* Minor refactoring of a private method to make it reusuable. * Adding a FasterRCNN + MobileNetV3 with & w/o FPN models. * Reducing Resolution to 320-640 and anchor sizes to 16-256. * Increase anchor sizes. * Adding rpn score threshold param on the train script. * Adding trainable_backbone_layers param on the train script. * Adding rpn_score_thresh param directly in fasterrcnn_mobilenet_v3_large_fpn. * Remove fasterrcnn_mobilenet_v3_large prototype and update expected file. * Update documentation and adding weights. * Use buildin Identity. * Fix spelling.
-
- 09 Nov, 2020 1 commit
-
-
Francisco Massa authored
* Remove model download from tests * Refactor trainable_layers checks in detection models * Bugfix * Finish tests and fixes * Fix lint
-
- 21 May, 2020 1 commit
-
-
Urwa Muaz authored
* 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
-
- 19 May, 2020 1 commit
-
-
Francisco Massa authored
* Make copy of targets in GeneralizedRCNNTransform * Fix flake8
-
- 15 May, 2020 1 commit
-
-
Urwa Muaz authored
* 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
-
- 16 Dec, 2019 1 commit
-
-
Francisco Massa authored
-
