Closed ShinoSpace closed 3 years ago
Yes, the final mask_feat_pred
is of scale 1/4 of the original image.
You can also check it by adding a mask_feat_pred.shape
print in the forward pass of single_stage_ins.py
Yes, the final
mask_feat_pred
is of scale 1/4 of the original image. You can also check it by adding amask_feat_pred.shape
print in the forward pass ofsingle_stage_ins.py
got it, thanks for your ans! appreciate!
I read through the entire code and found maybe a little different with paper solov2. these question are raised from solov2_head.py. here's my think:
split_feats
:is that means you use FPN features scale from 1/4 to 1/64, and the 1/4, 1/64 feature are down and up to 1/8, 1/32 respectively?
loss
->solov2_target_single
:when label assignment in method
loss
:is that means the unified representation is 1/4 scaled?
appreciate to your answer!