search

zzr-idam / 4KDehazing

81 stars 15 forks source link

about the loss function #6

Open LiMinghui19 opened 2 years ago

LiMinghui19 commented 2 years ago

Hi, thanks for your contribution. when I read your paper, you use l2 loss as your loss function. However, in your code, it seems like you used l1 loss, am I right?

Train.py：(line 25) mse = nn.L1Loss().cuda()

so, the result in your paper is obtained by L1 or L2 loss?

zzr-idam commented 2 years ago

In the paper, we use the l2 loss function as targer, but effect of the l1 is good.