You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In the blog article which led me to this code, the best result is with the "Pool layer method". You connect the pool layer from the CNN directly to the LSTM, instead of passing it through a softmax layer first.
In order to try both these suggestions myself, is it these lines in rnn_train.py that I have to change?
The first two lines (currently commented out) would be for the "pool layer method", and the second two lines (currently active) would be for the "softmax layer method"?
The text was updated successfully, but these errors were encountered:
In the blog article which led me to this code, the best result is with the "Pool layer method". You connect the pool layer from the CNN directly to the LSTM, instead of passing it through a softmax layer first.
In order to try both these suggestions myself, is it these lines in
rnn_train.py
that I have to change?The first two lines (currently commented out) would be for the "pool layer method", and the second two lines (currently active) would be for the "softmax layer method"?
The text was updated successfully, but these errors were encountered: