search

intel-analytics / BigDL-Tutorials

Step-by-step Deep Leaning Tutorials on Apache Spark using BigDL
208 stars 123 forks source link

One line change in rnn.py will be much more clear. #10

Closed cmusjtuliuyuan closed 7 years ago

cmusjtuliuyuan commented 7 years ago

https://github.com/intel-analytics/BigDL-Tutorials/blob/master/notebooks/neural_networks/rnn.py#L39 Change model.add(Select(2, 28)) to model.add(Select(2, -1))

By this way, we can emphasize that we select the last output of RNN layer.