Category "unity3d-unet"

dice coefficient and dice loss very low in UNET segmentation

I'm doing binary segmentation using UNET. My dataset is composed of images and masks. I divided the images and masks into different folders ( train_images, trai

CNN Prediction output to masked image

Given an output prediction of shape [1,21,388,88] from my Unet. How can I plot it as a masked image? I am using PASCAL dataset. Thanks!