mohammadfneish7 / keras_lstm_diagram Goto Github PK

Mohammad, great diagram, I noticed the parameter "shuffle" is mis-spelled (no "h") in the 4th text block under "Input Data".

Thank you Mohammad for the diagram, it's very useful however I'm a little confused about one thing.

In the part of the diagram showing the reshaped input data, one axis is labelled "No. of samples (batch size)" and in the text panel to the right under the Input Layer heading you describe the first axis of the 3D input as "No. of batches or samples". Is this intentional? It seems to imply Batch Size == No. of batches, or am I misunderstanding something here?

finally I got to your fancy explaination, midnight south Korea. really thank your for your dedication for sily like me. haha Thanks again!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

PS. if you don't mind, Can I translate it into Korean?

Greetings Mohammad and thanks for the useful diagram.

I wanted to clarify a few things regarding how LSTM handles operations with regard to different feature length / sequence length, and I came across this repo.

From your diagram (alone), it seems like the number of features affects the output dimension, while this, from my understanding, is depended only on the number of units.
You mention after all that the number of output units can be any number we desire.
Am I missing something? (regarding what the diagram shows)

Thanks,
Alex