1. 09 9月, 2021 4 次提交
  2. 08 9月, 2021 5 次提交
  3. 06 9月, 2021 1 次提交
  4. 05 9月, 2021 1 次提交
  5. 01 9月, 2021 4 次提交
  6. 31 8月, 2021 2 次提交
  7. 30 8月, 2021 8 次提交
  8. 29 8月, 2021 8 次提交
  9. 27 8月, 2021 3 次提交
  10. 26 8月, 2021 2 次提交
    • Glenn Jocher's avatar
      Auto-fix corrupt JPEGs (#4548) · 11f85e7e
      Glenn Jocher 提交于
      * Autofix corrupt JPEGs
      
      This PR automatically re-saves corrupt JPEGs and trains with the resaved images. WARNING: this will overwrite the existing corrupt JPEGs in a dataset and replace them with correct JPEGs, though the filesize may increase and the image contents may not be exactly the same due to lossy JPEG compression schemes. Results may vary by JPEG decoder and hardware.
      
      Current behavior is to exclude corrupt JPEGs from training with a warning to the user, but many users have been complaining about large parts of their dataset being excluded from training.
      
      * Clarify re-save reason
      11f85e7e
    • Glenn Jocher's avatar
      Fix for `python models/yolo.py --profile` (#4541) · 2da6444c
      Glenn Jocher 提交于
      Profiling fix copies input to Detect layer to circumvent inplace changes to the feature maps.
      2da6444c
  11. 23 8月, 2021 2 次提交