1. 02 Aug, 2022 1 commit
  2. 22 Jul, 2022 1 commit
  3. 08 Jul, 2022 1 commit
  4. 20 May, 2022 1 commit
  5. 19 May, 2022 1 commit
  6. 18 May, 2022 1 commit
  7. 09 May, 2022 1 commit
    • Yassine Alouini's avatar
      Distance IoU (#5786) · 1ae38297
      Yassine Alouini authored
      
      
      * [FEAT] Add distance IoU and distance IoU loss + some tests (WIP for tests).
      
      * [FIX] Remove URL from docstring + remove assert since it causes a big performance drop.
      
      * [FIX] eps isn't None.
      
      * [TEST] Update existing box dIoU test + add dIoU loss tests (inspired from cIoU ones).
      
      * [ENH] Some pre-commit fixes + remove print + mypy.
      
      * [ENH] Pass the device in the assertion for the dIoU loss test.
      
      * [FIX] Remove type hints from the dIoU box test.
      
      * [ENH] Refactor box and loss for dIoU functions + fix half tests.
      
      * [FIX] Precommits fix.
      
      * [ENH] Some improvement for the distance IoU tests thanks to code review.
      
      * [ENH] Upcast in distance boxes computation to avoid overflow.
      
      * [ENH] Revert the refactor of distance IoU loss back since it introduced a bug and can be slow.
      
      * Precommit fix.
      
      * [FIX] Few changes introduced by merge conflict.
      
      * Add code reference
      
      * Fix test
      Co-authored-by: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>
      1ae38297
  8. 28 Apr, 2022 1 commit
  9. 20 Apr, 2022 1 commit
  10. 19 Apr, 2022 1 commit
  11. 10 Apr, 2022 1 commit
  12. 05 Apr, 2022 1 commit
    • Vasilis Vryniotis's avatar
      Post-paper Detection Optimizations (#5444) · 08cc9a7f
      Vasilis Vryniotis authored
      * Use frozen BN only if pre-trained.
      
      * Add LSJ and ability to from scratch training.
      
      * Fixing formatter
      
      * Adding `--opt` and `--norm-weight-decay` support in Detection.
      
      * Fix error message
      
      * Make ScaleJitter proportional.
      
      * Adding more norm layers in split_normalization_params.
      
      * Add FixedSizeCrop
      
      * Temporary fix for fill values on PIL
      
      * Fix the bug on fill.
      
      * Add RandomShortestSize.
      
      * Skip resize when an augmentation method is used.
      
      * multiscale in [480, 800]
      
      * Add missing star
      
      * Add new RetinaNet variant.
      
      * Add tests.
      
      * Update expected file for old retina
      
      * Fixing tests
      
      * Add FrozenBN to retinav2
      
      * Fix network initialization issues
      
      * Adding BN support in MaskRCNNHeads and FPN
      
      * Adding support of FasterRCNNHeads
      
      * Introduce norm_layers in backbone utils.
      
      * Bigger RPN head + 2x rcnn v2 models.
      
      * Adding gIoU support to retinanet
      
      * Fix assert
      
      * Add back nesterov momentum
      
      * Rename and extend `FastRCNNConvFCHead` to support arbitrary FCs
      
      * Fix linter
      08cc9a7f
  13. 01 Apr, 2022 1 commit
  14. 29 Mar, 2022 1 commit
  15. 28 Mar, 2022 3 commits
  16. 15 Mar, 2022 1 commit
  17. 07 Mar, 2022 1 commit
  18. 27 Feb, 2022 1 commit
  19. 25 Feb, 2022 1 commit
  20. 24 Feb, 2022 1 commit
  21. 09 Feb, 2022 1 commit
  22. 08 Feb, 2022 2 commits
  23. 01 Feb, 2022 1 commit
  24. 24 Jan, 2022 1 commit
    • Joao Gomes's avatar
      Fix giou naming bug (#5270) · abdae5a1
      Joao Gomes authored
      * Adding multiweight support for shufflenetv2 prototype models
      
      * Revert "Adding multiweight support for shufflenetv2 prototype models"
      
      This reverts commit 31fadbee7d1a65cd73ae43dfd4ac6e97e7ca7b01.
      
      * Adding multiweight support for shufflenetv2 prototype models
      
      * Revert "Adding multiweight support for shufflenetv2 prototype models"
      
      This reverts commit 4e3d900f796c1e3e667312087e77956ca4a4c017.
      
      * Remove module vs method name clash
      abdae5a1
  25. 21 Jan, 2022 1 commit
    • Hu Ye's avatar
      add FCOS (#4961) · 7d4bdd43
      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: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>
      
      * Update torchvision/models/detection/fcos.py
      Co-authored-by: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>
      
      * Update torchvision/models/detection/fcos.py
      Co-authored-by: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>
      
      * Update torchvision/models/detection/fcos.py
      Co-authored-by: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>
      
      * Add FCOS model documentation
      
      * Fix typo in FCOS documentation
      
      * Add fcos to the prototype builder
      
      * Capitalize COCO_V1
      
      * Fix params of fcos
      
      * fix bug for partial
      
      * Fixing docs indentation
      
      * Fixing docs format in giou_loss
      
      * Adopt Reference for GIoU Loss
      
      * Rename giou_loss to generalized_box_iou_loss
      
      * remove overwrite_eps
      
      * Update AP test values
      
      * Minor fixes for the docs
      
      * Minor fixes for the docs
      
      * Update torchvision/models/detection/fcos.py
      Co-authored-by: default avatarZhiqiang Wang <zhiqwang@foxmail.com>
      
      * Update torchvision/prototype/models/detection/fcos.py
      Co-authored-by: default avatarZhiqiang Wang <zhiqwang@foxmail.com>
      Co-authored-by: default avatarzhiqiang <zhiqwang@foxmail.com>
      Co-authored-by: default avatarJoao Gomes <jdsgomes@fb.com>
      Co-authored-by: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>
      Co-authored-by: default avatarJoao Gomes <joaopsgomes@gmail.com>
      7d4bdd43
  26. 20 Jan, 2022 1 commit
    • Vasilis Vryniotis's avatar
      Adding ConvNeXt architecture in prototype (#5197) · afda28ac
      Vasilis Vryniotis authored
      * Adding CNBlock and skeleton architecture
      
      * Completed implementation.
      
      * Adding model in prototypes.
      
      * Add test and minor refactor for JIT.
      
      * Fix mypy.
      
      * Fixing naming conventions.
      
      * Fixing tests.
      
      * Fix stochastic depth percentages.
      
      * Adding stochastic depth to tiny variant.
      
      * Minor refactoring and adding comments.
      
      * Adding weights.
      
      * Update default weights.
      
      * Fix transforms issue
      
      * Move convnext to prototype.
      
      * linter fix
      
      * fix docs
      
      * Addressing code review comments.
      afda28ac
  27. 16 Dec, 2021 1 commit
  28. 09 Dec, 2021 1 commit
  29. 01 Dec, 2021 2 commits
  30. 30 Nov, 2021 1 commit
  31. 17 Nov, 2021 1 commit
  32. 02 Nov, 2021 1 commit
  33. 01 Nov, 2021 1 commit
  34. 29 Oct, 2021 2 commits
  35. 28 Oct, 2021 1 commit