search

idealo / image-super-resolution

🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
https://idealo.github.io/image-super-resolution/
Apache License 2.0
4.56k stars 755 forks source link

load initial weights #224

Open T-sara opened 2 years ago

T-sara commented 2 years ago

Dear cfrancesco,

How can I train, with initial weights?

As you suggested, I want to choose psnr loss for 50+ first epochs, then switch to gans. So when I start training with gans, I should load the resulting weights of last stage with psnr loss, am I correct?