Week1 Assignment1 conv_forward problem

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi,
I’m working on an assignment this week, and I’m getting an error in conv_forward.

The error is

—> 77 Z[i, h, w, c] = conv_single_step(a_slice_prev, weights, biases)
78
79 # YOUR CODE ENDS HERE

in conv_single_step(a_slice_prev, W, b)
23 # Z = None
24 # YOUR CODE STARTS HERE
—> 25 s = np.multiply(a_slice_prev, W)
26 Z = np.sum(s, keepdims=True, axis=None)
27 Z = np.sum(Z + np.float(b))

ValueError: operands could not be broadcast together with shapes (3,2,4) (3,3,4)

Can I get some advice on this? Thanks!

2

I suspect there is an error in your code for a_slice_prev in the conv_forward() function.