manuelfritsche / real-world-sr

[ICCVW 2019] PyTorch implementation of DSGAN and ESRGAN-FS from the paper "Frequency Separation for Real-World Super-Resolution". This code was the winning solution of the AIM challenge on Real-World Super-Resolution at ICCV 2019
MIT License
162 stars 37 forks source link

didn't match because some of the arguments have invalid types: (list, keepdim=bool) #14

Closed zhLawliet closed 4 years ago

zhLawliet commented 4 years ago

./PerceptualSimilarity/models/networks_basic.py return in_tens.mean([2,3],keepdim=keepdim) is right code?

change it as: kk = in_tens.mean(2,keepdim=keepdim) return kk.mean(3,keepdim=keepdim)