cszn / DnCNN

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)
https://cszn.github.io/
1.47k stars 539 forks source link

Question about learning rate decay #36

Closed AnnieZhong closed 6 years ago

AnnieZhong commented 6 years ago

Hello! I want to ask a question about the learning rate. In your paper “Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising”, you mentioned that “The learning rate was decayed exponentially from 1e-1 to 1e-4 for the 50 epochs”. I wonder how to do this in the code. Or any others can help me? Thank you very much!!!

cszn commented 6 years ago

logspace(-1,-4,50)