Closed yinhsunhuang closed 6 years ago
I've sent the PR(#14).
for i in range(self.n_layers):
output = F.relu(output)
layer_fnc = getattr(self, "gru"+str(i))
output = layer_fnc(output, hidden[i,:,:])
nh[i,:,:] = output
Why there's a Relu function between each layer?
Multilayer GRU seems wrong. In the original implementation, the weight of each layer is the same.
the for loop in forward() is using the same gru in each iteration/layer.