Detectron.pytorch icon indicating copy to clipboard operation
Detectron.pytorch copied to clipboard

Could not using RoiCrop in FPN backbone?

Open qinhaifangpku opened this issue 5 years ago • 0 comments

PLEASE FOLLOW THESE INSTRUCTIONS BEFORE POSTING

  1. Read the README.md thoroughly ! README.md is not a decoration.
  2. Please search existing open and closed issues in case your issue has already been reported
  3. Please try to debug the issue in case you can solve it on your own before posting

After following steps above and agreeing to provide the detailed information requested below, you may continue with posting your issue

(Delete this line and the text above it.)

Expected results

What did you expect to see?

Actual results

What did you observe instead?

Detailed steps to reproduce

E.g.:

The command that you ran

System information

  • Operating system: ?
  • CUDA version: ?
  • cuDNN version: ?
  • GPU models (for all devices if they are not all the same): ?
  • python version: ?
  • pytorch version: ?
  • Anything else that seems relevant: ?

Hi, I found that the RoiCrop using the affine_grid_gen function in net.py. Every roi in rois will divide 16. I think it means the feat stride. But there are levels in FPN backbones. Anyone could tell me how to use RoiCrop in FPN Backbone?

qinhaifangpku avatar Oct 08 '18 11:10 qinhaifangpku