Closed ekerazha closed 8 years ago
You can now use the keyword argument batch_input_shape
to specify an input shape that includes the batch size. I'll fix the error message.
@fchollet : I am still getting this error despite using batch_input_shape
check cell 20 in this notebook https://github.com/anujgupta82/DeepNets/blob/master/LSTM/IMDB_Embedding_w2v_LSTM_3.ipynb
Have a look at that : http://philipperemy.github.io/keras-stateful-lstm/
I'm trying the stateful RNN implementation. This is my code:
But I get this error:
Please note that I provide both input_dim and input_length. I also tried to provide input_shape, but I got the same error. Moreover it says "including batch size", but there isn't any "batch_size" parameter.
In layers/recurrent.py there's this code:
If I print input_shape I get (None, input_length, input_dim), so it raises an exception because input_shape[0] is "None". What is that first parameter?