Closed jorgyz closed 8 years ago
Hi, how did you get your HR image? I met this problem when I use imresize function from python version opencv. You can check the value in these pixels, are they NAN?
Thanks for your response. I fixed the issue...it was due to negative values in the output from the network. I replaced them with zero before converting back to RGB and it fixed the problem. Thanks!
jorgyz, I need your help !
Did you solve the issue with Caffe SegNet ?
[https://github.com/alexgkendall/caffe-segnet/issues/24])
I have similar problem, can you help me ?
Hi,
I have successfully trained a model and the output images look good, with one exception. For some reason I get a lot of stray white pixels in dark areas of the image. I have attached an example. Some images only have a few of these stray pixels, while others (like this one) have many. Any idea what might be causing this?
Thanks!