I'm new in using keras and Unet for the segmentation of the images. I am using a code already done from which to start and wanted to know how I could get an accuracy value, iou_score in this case, for each image in the test, not just the total average.
the already done code I am using is the following: https://github.com/qubvel/segmentation_models/blob/master/examples/binary%20segmentation%20(camvid).ipynb
What I want to achieve is to have an accuracy value for each predicted image. In this image, for example, I would like an accuracy for each prediction, so 3 different values, one per line. image
