Created
January 30, 2016 05:26
-
-
Save kylemcdonald/ff2aaa33b78f9fb48867 to your computer and use it in GitHub Desktop.
A bug in Keras?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi, I have a question. Suppose I have a dataframe of 23347 rows x 380 columns. What is the correct
input_shape
for Convolution1D? with(1, 380)
and(None, 380)
, I can't get the model to compile.But if I use
(10, 380)
, my model compiles but I can't fit it.