search

implus / GFocal

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, NeurIPS2020
Apache License 2.0
587 stars 73 forks source link

How to draw correlation curve about IoU score and classification score? #19

Open black12357 opened 3 years ago

black12357 commented 3 years ago

Thank you for your great work! I wonder whether you can share the idea about how to make statistics of IoU score and classification score to draw the correlation curve in figure 2.b of your paper?

If it's possible, could you share the code? Thank you so much!

implus commented 3 years ago

An easy and simple way to get the statistics of IoU score and classification score is: 1) log the statistics to some txt files by writing codes in function loss_single() of https://github.com/implus/GFocal/blob/master/mmdet/models/anchor_heads/gfl_head.py 2) run training command to get these txt files filled with the information you need

The code is easy to implement.

black12357 commented 3 years ago

Thank you for your help! I already tried it and get success.

pauliustumas commented 3 years ago

Thank you for your help! I already tried it and get success.

Any sample code?