W1 A3 djmodel

Course Q&A Deep Learning Specialization Sequence Models
1

I’m having some trouble doing the djmodel exercise; i get the error:

InvalidArgumentError: Input to reshape is a tensor with 2 values, but the requested shape has 180 [Op:Reshape]
with this

    x = reshaper((1, n_values))(x)
2

The reshaper object already has the shape tuple specified here:

image
image753×119 4.35 KB

You don’t need to repeat that portion. In your code, delete the shape tuple, and just pass the (x) data.

1 Like
3

I got the same line and the same error as the original post. When I remove the tuple, I got the following error:

ValueError: The first argument to Layer.call must always be passed.

4

I fixed the error. I should have removed not only the tuple but the paranthesis, leaving only the (x).

1 Like