about your code

[suoranxiu]

Dear Jiwoon Ahn:
I'm a student who is studying your great paper -- Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation . When I run your code from github, finding an error. The error is in the picture. I would appreciate it if you can give me some tips on your code.
Thank you very much.

RuntimeError: size mismatch, m1: [1 x 20], m2: [1 x 20]