ValueError: Input 0 of layer lstm_12 is incompatible with the layer: expected ndim=3, found ndim=4

user_13610320 0
Viewed 131

I am working on seq2seq model, and I want to use the embedding layer given in Keras Blog Bonus FAQ. Here is my code, where num_encoder_tokens is 67 and num_decoder_tokens is 11. enter image description here

I am getting the issue shown in figure. enter image description here

Can anyone help me with reshaping the output_shape of embedding layer or input shape of LSTM as I have no idea how to do it.

seq2seq lstm keras tensorflow python
0 Answers
Related