Hi guys,
I am working on this nice package (and thank you Nils for making this available) I want to add one FC layer to the network. however, when data is fed to the network, the output does not have the gradient attached to it and hence, it looses information that is needed for back propagation.
i am able to incorporate ESNCell.py into my network and run backprop in it. however, if I use the ridge regression cell (RRCell.py) it generates an output that does not have the gradient and therefore no backprop on its output.
I used both ESN.py , LiESN.py, and after calling the finalize method, and then testing the network, the output does not have the gradient.
for example:
esn= esn = etnn.LiESN(input_dim=input_dim, hidden_dim=n_hidden, output_dim=1, spectral_radius=spectral_radius, learning_algo='inv', leaky_rate=leaky_rate)
esn(inputs,targets)
esn.finalize()
y_predicted=esn(inputs)
and then y_predicted is just a tenson without any gradient attached to it
any suggestions? @nschaetti
I've been suffering a problem with feeding the network.
I made several tris, with normal label and hot_encoded version either. Than I modify the dimension of the target into (output,batch_size) and I always cross this error: Dimension out of range (expected to be in range of [-1, 0], but got 1)
