Exercise 3 - conv_forward

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hello,

I’m running into an issue with Exercise 3. I get the following error and am stuck. Any ideas what may be causing it?

ValueError Traceback (most recent call last)
in
6 “stride”: 2}
7
----> 8 Z, cache_conv = conv_forward(A_prev, W, b, hparameters)
9 print(“Z’s mean =\n”, np.mean(Z))
10 print(“Z[0,2,1] =\n”, Z[0, 2, 1])

in conv_forward(A_prev, W, b, hparameters)
81 print(“Z”, Z)
82 print("Z shape ", Z.shape)
—> 83 Z[i, h, w, c] = np.sum(np.dot(weights, a_slice_prev)) + biases
84 # YOUR CODE STARTS HERE
85

ValueError: setting an array element with a sequence.

2

Hi jose.bulatao,

It may be useful to use your function conv_single_step.

In any case, you want element-wise multiplication rather than the dot product.