An error about the concatenate layer

Course Q&A Deep Learning Specialization Sequence Models
1

I am confused about the error I am getting when summary is called in the test code in Assignment 1 of Week 3 of Course 5:

AttributeError: The layer “concatenate” has multiple inbound nodes, with different output shapes.
Hence the notion of “output shape” is ill-defined for the layer. Use
get_output_shape_at(node_index) instead.

The only concatenation layer I am aware of is in one_step_attention(). There we concatenate a and s_prev (the latter after being repeated). I print out the shapes of both before concatenation and they are same: (None, 30, 64).

What could I be doing wrong?

2

Hi @Meir

Have you found the solution yet? Let’s know if we could help.

3

I don’t remember what I did, but I am past this problem. Thank you.

4

You have to restart the kernel

3 Likes