Closed dearkafka closed 7 years ago
My understanding, that you are running a few iterations adding (?) blocks and checking whether the network started predicting, is it correct?
No. My neural networks had 4 outputs (malignancy, lobulation, diameter, spiculation). Think of two extremes when it comes to a multi output problem:
I found neither of these to be ideal. What I found worked best was to share the lower layers in the network between each output but stop parameter sharing after a few layers. It's sort of a hybrid between the two extremes.
Take a look here for an example, starting around line 58. There is one conv layer per output, and the conv layers no longer interact any more. Before this all the conv layers were shared between outputs.
Thank you, Daniel, that was helpful.
Could you elaborate what do you mean by "branching":
My understanding, that you are running a few iterations adding (?) blocks and checking whether the network started predicting, is it correct?