Error with conv_forward_test()

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I am getting with error on function conv_forward()

Z's mean =
 0.3519500704507587
Z[0,2,1] =
 [ -3.01280755  -2.90226517  -8.34171936  -5.26220853   5.6630696
   1.08704033   2.20430705 -10.73218294]
cache_conv[0][1][2][3] =
 [-1.1191154   1.9560789  -0.3264995  -1.34267579]
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-68-182241fd5e53> in <module>
     11 print("cache_conv[0][1][2][3] =\n", cache_conv[0][1][2][3])
     12 
---> 13 conv_forward_test(conv_forward)

~/work/release/W1A1/public_tests.py in conv_forward_test(target)
    296     assert Z_shape[3] == W.shape[3], f"n_C is wrong. Current: {Z_shape[3]}.  Expected: {W.shape[3]}"
    297 
--> 298     Z, cache_conv = target(A_prev, W, b, {"pad" : 0, "stride": 2})
    299     assert(Z.shape == (2, 2, 3, 8)), "Wrong shape. Don't hard code the pad and stride values in the function"
    300 

<ipython-input-67-7dadac1fa933> in conv_forward(A_prev, W, b, hparameters)
    103                     biases = b[:,:, :, c]
    104 
--> 105                     Z[i, h, w, c] = conv_single_step(a_slice_prev, weights, biases)
    106 
    107     # YOUR CODE ENDS HERE

<ipython-input-4-b2ecf972598e> in conv_single_step(a_slice_prev, W, b)
     23     # Z = None
     24     # YOUR CODE STARTS HERE
---> 25     s = a_slice_prev *  W
     26     Z = np.sum(s)
     27     Z = Z + float(b)

ValueError: operands could not be broadcast together with shapes (0,3,4) (3,3,4)

I am not understanding how I am getting this error on function conv_single_step(a_slice_prev, W, b) , if it was previously working properly…

1 Like
2

Hi Gloria,

Excuses for the belated reply. Have you been able to resolve this issue?

3

Hi!
In the end, yes. The error was related to the wrong stride index during for loop.

1 Like
4

Happy to hear it! Good luck with the rest of the course!