Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

where is the code for the "Pool layer method" #3

Open
chrisrapson opened this issue Aug 6, 2019 · 0 comments
Open

where is the code for the "Pool layer method" #3

chrisrapson opened this issue Aug 6, 2019 · 0 comments

Comments

@chrisrapson
Copy link

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?

 # filename = 'data/cnn-features-frames-1.pkl'
 # input_length = 2048
 filename = 'data/predicted-frames-1.pkl'
 input_length = 2

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"?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant