- 28 Jan, 2020 1 commit
-
-
Francisco Massa authored
* torchscriptable functions for video io (#1653) Summary: Pull Request resolved: https://github.com/pytorch/vision/pull/1653 created new torchscriptable video io functions as part of the api: read_video_meta_data_from_memory and read_video_from_memory. Updated the implementation of some of the internal functions to be torchscriptable. Reviewed By: stephenyan1231 Differential Revision: D18720474 fbshipit-source-id: 4ee646b66afecd2dc338a71fd8f249f25a3263bc * BugFix Co-authored-by:
Jon Guerin <54725679+jguerin-fb@users.noreply.github.com>
-
- 16 Dec, 2019 1 commit
-
-
Oana Florescu authored
* remove windows skips from video_utils tests, now that they pass * replace lambda in videoclips in order to be pickled on windows and update tests
-
- 10 Dec, 2019 1 commit
-
-
James Thewlis authored
-
- 07 Nov, 2019 1 commit
-
-
Henry Xia authored
-
- 31 Oct, 2019 1 commit
-
-
Rahul Somani authored
-
- 29 Oct, 2019 1 commit
-
-
Francisco Massa authored
* Unify video metadata in VideoClips * Bugfix * Make tests a bit more robust
-
- 08 Oct, 2019 1 commit
-
-
Zhicheng Yan authored
-
- 03 Oct, 2019 1 commit
-
-
Zhicheng Yan authored
* add metadata to video dataset classes. bug fix. more robustness * query video backend within VideoClips class * Fix tests * Fix lint
-
- 24 Sep, 2019 2 commits
-
-
ekosman authored
* Expose num_workers in VideoClips * add documentation for num_workers in VideoClips * add documentation for num_workers in VideoClips * add documentation for num_workers in VideoClips
-
Zhicheng Yan authored
* add _backend argument to __init__() of class VideoClips * minor fix * minor fix * Make backend private in VideoClips * Fix lint
-
- 23 Sep, 2019 1 commit
-
-
ekosman authored
-
- 31 Jul, 2019 2 commits
-
-
Francisco Massa authored
* Move RandomClipSampler to references * Lint and bugfix
-
Francisco Massa authored
* Copy classification scripts for video classification * Initial version of video classification * add version * Training of r2plus1d_18 on kinetics work Gives even slightly better results than expected, with 57.336 top1 clip accuracy. But we count some clips twice in this evaluation * Cleanups on training script * Lint * Minor improvements * Remove some hacks * Lint
-
- 26 Jul, 2019 1 commit
-
-
Francisco Massa authored
* Miscellaneous fixes and improvements * Guard against videos without video stream * Fix lint * Add test for packed b-frames videos * Fix missing import
-
- 23 Jul, 2019 1 commit
-
-
Francisco Massa authored
-
- 19 Jul, 2019 1 commit
-
-
Francisco Massa authored
* Add VideoClips and Kinetics dataset * Lint + add back missing line * Adds ClipSampler following Bruno comment * Change name following Bruno's suggestion * Enable specifying a target framerate * Fix test_io for new interface * Add comment mentioning drop_last behavior * Make compute_clips more robust * Flake8 * Fix for Python2
-