1. 08 May, 2023 1 commit
  2. 23 Mar, 2023 2 commits
  3. 27 Feb, 2023 2 commits
  4. 24 Feb, 2023 3 commits
  5. 23 Feb, 2023 2 commits
  6. 21 Feb, 2023 1 commit
  7. 17 Feb, 2023 2 commits
  8. 16 Feb, 2023 2 commits
  9. 15 Feb, 2023 2 commits
  10. 14 Feb, 2023 2 commits
  11. 13 Feb, 2023 2 commits
  12. 08 Feb, 2023 1 commit
  13. 24 Jan, 2023 1 commit
  14. 20 Jan, 2023 1 commit
  15. 11 Jan, 2023 1 commit
  16. 05 Dec, 2022 1 commit
  17. 30 Nov, 2022 1 commit
  18. 04 Nov, 2022 1 commit
  19. 27 Oct, 2022 1 commit
    • Vasilis Vryniotis's avatar
      [prototype] Minor speed and nit optimizations on Transform Classes (#6837) · e1f464bd
      Vasilis Vryniotis authored
      * Change random generator for ColorJitter.
      
      * Move `_convert_fill_arg` from runtime to constructor.
      
      * Remove unnecessary TypeVars.
      
      * Remove unnecessary casts
      
      * Update comments.
      
      * Minor code-quality changes on Geometical Transforms.
      
      * Fixing linter and other minor fixes.
      
      * Change mitigation for mypy.`
      
      * Fixing the tests.
      
      * Fixing the tests.
      
      * Fix linter
      
      * Restore dict copy.
      
      * Handling of defaultdicts
      
      * restore int idiom
      
      * Update todo
      e1f464bd
  20. 24 Oct, 2022 1 commit
    • Vasilis Vryniotis's avatar
      Adding Uniform temporal Subsampling for Video (#6812) · e96860d6
      Vasilis Vryniotis authored
      
      
      * Adding temporal sampling kernel and dispatcher.
      
      * Adding the UniformTemporalSubsample class.
      
      * Add it on init
      
      * Adding tests.
      
      * Addressing comments.
      
      * Reverting proposal as it led to different results.
      
      * add more tests for uniform_temporal_subsample
      
      * cleanup
      
      * fix logic
      
      * fix logic
      
      * make test more strict
      
      * lint
      
      * Update torchvision/prototype/transforms/functional/_temporal.py
      
      * remove pytorchvideo again per request
      Co-authored-by: default avatarPhilip Meier <github.pmeier@posteo.de>
      e96860d6
  21. 21 Oct, 2022 2 commits
  22. 14 Oct, 2022 2 commits
  23. 13 Oct, 2022 1 commit
  24. 11 Oct, 2022 1 commit
    • Vasilis Vryniotis's avatar
      [prototype] Switch to `spatial_size` (#6736) · 4d4711d9
      Vasilis Vryniotis authored
      * Change `image_size` to `spatial_size`
      
      * Fix linter
      
      * Fixing more tests.
      
      * Adding get_num_channels_video and get_spatial_size_* kernels for video, masks and bboxes.
      
      * Refactor get_spatial_size
      
      * Reduce the usage of `query_chw` where possible
      
      * Rename `query_chw` to `query_spatial_size`
      
      * Adding `get_num_frames` dispatcher and kernel.
      
      * Adding jit-scriptability tests
      4d4711d9
  25. 10 Oct, 2022 1 commit
  26. 07 Oct, 2022 2 commits
    • Philip Meier's avatar
      replace new_like with wrap_like (#6718) · 4c049ca3
      Philip Meier authored
      * replace new_like with wrap_like
      
      * fix videos
      
      * revert casting in favor of ignoring mypy
      4c049ca3
    • Philip Meier's avatar
      add Video feature and kernels (#6667) · 3118fb52
      Philip Meier authored
      * add video feature
      
      * add video kernels
      
      * add video testing utils
      
      * add one kernel info
      
      * fix kernel names in Video feature
      
      * use only uint8 for video testing
      
      * require at least 4 dims for Video feature
      
      * add TODO for image_size -> spatial_size
      
      * image -> video in feature constructor
      
      * introduce new combined images and video type
      
      * add video to transform utils
      
      * fix transforms test
      
      * fix auto augment
      
      * cleanup
      
      * address review comments
      
      * add remaining video kernel infos
      
      * add batch dimension squashing to some kernels
      
      * fix tests and kernel infos
      
      * add xfails for arbitrary batch sizes on some kernels
      
      * fix test setup
      
      * fix equalize_image_tensor for multi batch dims
      
      * fix adjust_sharpness_image_tensor for multi batch dims
      
      * address review comments
      3118fb52
  27. 03 Oct, 2022 1 commit