loss during training about caffe-vdsr HOT 4 CLOSED

x2 loss: 0.16~0.17
training sample size 41x41

from caffe-vdsr.

Thanks @huangzehao .
What's the gray level of your input image? is it [0,1] or [0,255]?
if my input is between [0,1], since the EuclideanLoss E = 1/2N×sum((y-y')^2), shall I expect the max loss to be 0.5?

Jianyu

from caffe-vdsr.

Hi, the gray level of input image is [0,1].
The max loss is not 0.5, since the output of the network is not limit to [0,1].

from caffe-vdsr.

Thanks. I am using similar networks, with EuclideanLoss layer. My input is [0,255], but I stretch that into [0,1], using
transform_param {
scale: 0.00390625
}
In that way, I end up with loss ~1k when convergence, with fixed learning rate, without fine-tuning. The output during testing still seems to make sense. So I wonder is this 1k loss I got the result of 256*Euclidean loss?

from caffe-vdsr.