I reimplement your model (Teacher: R101, Student: R50, Detection head: Foveabox) and got RuntimeError: shape '[-1, 68]' is invalid for input of size 115200

[letruongngochai]

Hello, here I try to replace the detection head used with Foveabox. I use R50 as a student and R101 as a teacher to distill. But I can't manage to train it due to the above error. Is there any advices in changing the detection head of your model that you can give me? Thanks

[HikariTJU]

Have you modified the head to use general distribution? Like what I did in atss_gfl_head.py

[letruongngochai]

Can you tell me where to view the .py file you mentioned?

[HikariTJU]

https://github.com/HikariTJU/LD/blob/main/mmdet/models/dense_heads/atss_gfl_head.py

1. you need to change network from 4-d ltrb to 4x17 distribution (refer to GFocal)
   

   LD/mmdet/models/dense_heads/atss_gfl_head.py

   Line 120 in bc60bbc

   self.atss_reg = nn.Conv2d(

2. when calculate bbox loss use integral to transform 4x17 distribution back to 4-d ltrb
   

   LD/mmdet/models/dense_heads/atss_gfl_head.py

   Line 252 in bc60bbc

   pos_bbox_pred_corners = self.integral(pos_bbox_pred)

[letruongngochai]

Sorry but I just don't get the "4-d ltrb" point, what is it actually?

[HikariTJU]

ltrb is introduced in FCOS to replace xywh, I know a little about FoveaBox, maybe you should change xywh to ltrb at first