search

zejinwang / Blind2Unblind

This is an official implementation of the CVPR2022 paper "Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots".
https://arxiv.org/abs/2203.06967
118 stars 13 forks source link

Loss doesn't converge #22

Open yashkhurana24 opened 7 months ago

yashkhurana24 commented 7 months ago

Hello, I'm trying to denoise a 2D image. I add synthetic noise as follows: np.array(np.random.poisson(0.01 * x / 0.1) / 0.01 But the loss doesn't converge. I have several different learning rates. Can you help me out?

Fe K

zejinwang commented 7 months ago

If the training set is small, you'd better set the initial learning rate to 10 times larger. Besides, it is normal that the trend of decreasing loss is not obvious.