Why the dsgan's pretrained models can't uncompress?

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

Why the dsgan's pretrained models can't uncompress? #8

Closed zrongcheng closed 4 years ago

zrongcheng commented 4 years ago

Thanks for your works, It help me more. But, All of them can't uncompress

danielkaifeng commented 4 years ago

I met the same problem. How did you solve it?

zrongcheng commented 4 years ago

It's not compressed file, just look the dsgan/train.py.

danielkaifeng commented 4 years ago

Thank you! I just waste half an hour to figure out this problem...