3 classification

[maswyp]

Hello I am trying to use unet on a custom data set of labels that have the standard 3 RGB channels. My question is how would I configure the mask for each image given that there are three different classifications I want?

[mingzhaochina]

So,where is the data?

[maswyp]

Thanks for your reply, i find a way to solve this problem, just replace the output of the network lay to 3 and rewrite loss function

[mingzhaochina]

Thanks!May I ask for 3 classification did you make a label for every class separately?In this code the label has only one channel,it is impossible to calculate loss function because the label and the data don't have the same shape.

[maswyp]

I use one-hot code to divide the label, my loss function is 1-dice/class