1. 30 Nov, 2020 1 commit
  2. 27 Nov, 2020 4 commits
    • Vasilis Vryniotis's avatar
      Support for image with no annotations in RetinaNet (#3032) · 4ab46e5f
      Vasilis Vryniotis authored
      * Enable support for images without annotations
      
      * Ensuring gradient propagates to RegressionHead.
      
      * Rewriting losses to remove branching.
      
      * Fix the seed on DeformConv autocast test.
      4ab46e5f
    • Vasilis Vryniotis's avatar
      9e71fdaf
    • vfdev's avatar
      [BC-breaking] Introduced InterpolationModes and deprecated arguments: resample... · 0c445130
      vfdev authored
      [BC-breaking] Introduced InterpolationModes and deprecated arguments: resample and fillcolor (#2952)
      
      * Deprecated arguments: resample and fillcolor
      Replaced by interpolation and fill
      
      * Updates according to the review
      
      * Added tests to check warnings and asserted BC
      
      * [WIP] Interpolation modes
      
      * Added InterpolationModes enum
      
      * Added supported for int values for interpolation for BC
      
      * Removed useless test code
      
      * Fix flake8
      0c445130
    • Aditya Oke's avatar
      Add utility to draw bounding boxes (#2785) · 240210c9
      Aditya Oke authored
      
      
      * initital prototype
      
      * flake
      
      * Adds documentation
      
      * minimal working bboxes
      
      * Adds label display
      
      * adds colors :-)
      
      * adds suggestions and fixes CI
      
      * handles image of dim 4
      
      * fixes image handling
      
      * removes dev file
      
      * adds suggested changes
      
      * Updating the API.
      
      * Update test.
      
      * Implementing code review improvements.
      
      * Further refactoring and adding test.
      
      * Replace random to white to reduce size and change font on tests.
      Co-authored-by: default avatarVasilis Vryniotis <vvryniotis@fb.com>
      240210c9
  3. 26 Nov, 2020 1 commit
  4. 20 Nov, 2020 2 commits
    • Vasilis Vryniotis's avatar
      Refactor & enable JIT tests in all models and add warnings if skipped (#3033) · 4521f6d1
      Vasilis Vryniotis authored
      * Enable jit tests in all models and add warning if checkModule() tests are skipped.
      
      * Turning on JIT tests on CI.
      
      * Fixing broken unit-tests.
      
      * Refactoring and cleaning up duplicate code.
      4521f6d1
    • Alexey Demyanchuk's avatar
      Add explicit check for number of channels (#3013) · a51c49e4
      Alexey Demyanchuk authored
      
      
      * Add explicit check for number of channels
      
      Example why you need to check it:
      `M = torch.randint(low=0, high=2, size=(6, 64, 64), dtype = torch.float)`
      When you put this input through to_pil_image without mode argument, it converts to uint8 here:
      ```
      if pic.is_floating_point() and mode != 'F':
                  pic = pic.mul(255).byte()
      ```
      and change the mode to RGB here:
      ```
      if mode is None and npimg.dtype == np.uint8:
                  mode = 'RGB'
      ```
      Image.fromarray doesn't raise if provided with mode RGB and just cut number of channels from what you have to 3
      
      * Check number of channels before processing
      
      * Add test for invalid number of channels
      
      * Add explicit check for number of channels
      
      Example why you need to check it:
      `M = torch.randint(low=0, high=2, size=(6, 64, 64), dtype = torch.float)`
      When you put this input through to_pil_image without mode argument, it converts to uint8 here:
      ```
      if pic.is_floating_point() and mode != 'F':
                  pic = pic.mul(255).byte()
      ```
      and change the mode to RGB here:
      ```
      if mode is None and npimg.dtype == np.uint8:
                  mode = 'RGB'
      ```
      Image.fromarray doesn't raise if provided with mode RGB and just cut number of channels from what you have to 3
      
      * Check number of channels before processing
      
      * Add test for invalid number of channels
      
      * Put check after channel dim unsqueeze
      
      * Add test if error message is matching
      
      * Delete redundant code
      
      * Bug fix in checking for bad types
      Co-authored-by: default avatarDemyanchuk <demyanca@mh-hannover.local>
      Co-authored-by: default avatarvfdev <vfdev.5@gmail.com>
      a51c49e4
  5. 19 Nov, 2020 2 commits
  6. 18 Nov, 2020 2 commits
    • Zhiqiang Wang's avatar
      Adds Anchor tests with ground-truth outputs (#2983) · b18a4757
      Zhiqiang Wang authored
      * Add AnchorGenerator with ground-truth outputs
      
      * Minor fixes
      b18a4757
    • Vasilis Vryniotis's avatar
      Support specifying output channels in io.image.read_image (#2988) · 4d6ba678
      Vasilis Vryniotis authored
      * Adding output channels implementation for pngs.
      
      * Adding tests for png.
      
      * Adding channels in the API and documentation.
      
      * Fixing formatting.
      
      * Refactoring test_image.py to remove huge grace_hopper_517x606.pth file from assets and reduce duplicate code. Moving jpeg assets used by encode and write unit-tests on their separate folders.
      
      * Adding output channels implementation for jpegs. Fix asset locations.
      
      * Add tests for JPEG, adding the channels in the API and documentation and adding checks for inputs.
      
      * Changing folder for unit-test.
      
      * Fixing windows flakiness, removing duplicate test.
      
      * Replacing components to channels.
      
      * Adding reference for supporting CMYK.
      
      * Minor changes: num_components to output_components, adding comments, fixing variable name etc.
      
      * Reverting output_components to num_components.
      
      * Replacing decoding with generic method on tests.
      
      * Palette converted to Gray.
      4d6ba678
  7. 12 Nov, 2020 2 commits
  8. 10 Nov, 2020 2 commits
  9. 09 Nov, 2020 5 commits
  10. 06 Nov, 2020 2 commits
    • vfdev's avatar
      House keeping improvements: (#2964) · f655e6a7
      vfdev authored
      - fixed problem with error computation between results
      - refactored tensor cast for resize
      - fixed round usage
      f655e6a7
    • Vasilis Vryniotis's avatar
      Fix flakiness on detection tests (#2966) · 7f7ff056
      Vasilis Vryniotis authored
      * Simplify the ACCEPT=True logic in assertExpected().
      
      * Separate the expected filename estimation from assertExpected
      
      * Unflatten expected values.
      
      * Assert for duplicate scores if primary check fails.
      
      * Remove custom exceptions for algorithms and add a compact function for shrinking large ouputs.
      
      * Removing unused variables.
      
      * Add warning and comments.
      
      * Re-enable all autocast unit-test for detection and marking the tests as skipped in partial validation.
      
      * Move test skip at the end.
      
      * Changing the warning message.
      7f7ff056
  11. 05 Nov, 2020 1 commit
  12. 04 Nov, 2020 2 commits
  13. 03 Nov, 2020 1 commit
  14. 30 Oct, 2020 2 commits
  15. 22 Oct, 2020 2 commits
  16. 21 Oct, 2020 3 commits
  17. 20 Oct, 2020 1 commit
  18. 16 Oct, 2020 2 commits
  19. 14 Oct, 2020 3 commits