Training with more than four channels
astillich opened this issue · comments
I have an image with three different shapes and another image with 4 classes, 3 marking the shapes and one class for marking the background. I created a .CTensor from these and wrote a .set file which associates the colors to classes using
makeCompressedTensorStream testclass.set images . labels . testclass.CTensor false
When I try to train a network with the four classes, CN24 errors out with:
ERR [ ErrorLayer::CreateOutputs(49) ] Inputs need the same number of elements!
The same also happens when I modify the toy example to use four classes.
Am I missing something or is that a bug?
EDIT: this is on master, not develop
Could you post the dimensions of each entry in the Tensor stream? While CN24 may make some assumptions about the number of input channels, no such restrictions exist on output channels.
TOY.Tensor
My test tensor:
