Python script to run different architectures

[Pilar O]

In the documentation, when talking about recipes, for example, lstm, it talks about a script called “./run_lstm.py”, should we use this one to run a config file with lstm or can we keep using ./run_dnn.py? any differences?

Thanks.

[Simon]

I believe you can (and should) now switch to using run_lstm.py in all cases, both LSTM and purely feed-forward architectures.

[Simon]

Also, I think that run_dnn.py might be hardwired to use only tanh layers regardless of what the configuration file specifies.

[Author]

Posts