Leotju/MGAN

Predictions from MGA layer used in loss function?

Opened this issue · 1 comments

NehalD99 commented

Hello,

I would like to ask whether the predictions from the MGA layer were directly used in the BCE Loss as stated in the paper? How did you modify the prediction output size(7x7) to match the visible box coarse annotation?

Thank you,
Nehal

Leotju commented
  1. The loss is the same as stated in the paper.
  2. You could crop and resize the ground thuth.