Closed connectedhealthcaremy closed 5 years ago
how to define hidden we have randomly selected the hidden but its becoming zero when computing the output please help us to resolve this issue for classificattion
All the remaining issues resolved code running succcessfully but the output we are getting for classification is just single vector. Do we need to give target in the form of (1,0)(0,1) or singlevector (0,1,1,0)
It depends on your loss function. I added two examples to the repository. You should take a look to mnist.py
classification task.
we have run the code and we have put the features in tensor object for classification but we are getting following exception AttributeError: 'int' object has no attribute 'dim' can you help in elobrating us why this exception is coming The below are the lines at which it was coming if input.dim() == 2 and bias is not None:
fused op is marginally faster