guava1427
guava1427
Hello, I'm trying to use your network. For the multi-labelled segmentation, what is the proper structure in case of the labelled data? Your code seems to load *.tfrecord (generated from...
Hello, I tried to use AC or ACE losses instead of CE loss for the binary segmentation. Though I have used a certain network for the CE loss many times,...
Thank you for this insightful work. I found that the variable 'dst' (x, y, and confidence) corresponds to the key points in an image, but I could not find the...