Open 314rated opened 6 years ago
Hi, have you already checked your images? I had a similar issue (I was also working on a 2-class problem) 'cause the image values were 0 for 'class 1' and 255 for the second one instead of 0 and 1.
The real images are colored images (128x128x3). The masked images are (128x128x1), but not 0-1 valued. I modified ImageDataProvider._load_file to make masked image to 0/1 array. It still gives same results. Anyhow, the mask is being read in boolean, so it should not matter, right?
Hi, I am trying to do binary segmentation on 128x128 images. Padding is done on them to ensure outputed image is also 128x128 (as per your kind suggestion). The number of classes = 2 (one is background, other is object). However, the U-net is giving total white output in the entire image. It is not separating between object and background. I have tried both the losses as provided by Unet, changed the number of layers, and feature roots. Could you please suggest any other steps that can be taken to remedy this? Thanks