Week 2 Assignment 1 Exercise 2

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I am getting the following error after editing the code as I should have. I would appreciate guidance, as I followed the markdown exactly.

print(X):
tf.Tensor(
[[[[0. 0. 0. 0.03106003 0. 0.222367 ]
[0. 0. 0. 0.01449109 0. 0.11191814]]

[[0. 0. 0. 0.00742243 0. 0.187996 ]
[0. 0. 0. 0. 0. 0.11683747]]]

[[[0. 0. 0. 0.25271386 0. 0.57789576]
[0. 0. 0. 0.02845018 0. 0.49135414]]

[[0. 0. 0. 0.4180615 0. 0.48207274]
[0. 0. 0. 0.10254528 0. 0.4299419 ]]]

[[[0. 0. 0. 0.75796723 0. 1.7334964 ]
[0. 0. 0. 0.08518484 0. 1.4741935 ]]

[[0. 0. 0. 1.254309 0. 1.4462117 ]
[0. 0. 0. 0.3074641 0. 1.2898763 ]]]], shape=(3, 2, 2, 6), dtype=float32)

AssertionError Traceback (most recent call last)
Input In [33], in <cell line: 3>()
1 ### you cannot edit this cell
----> 3 public_tests.convolutional_block_test(convolutional_block)

File /tf/W2A1/public_tests.py:106, in convolutional_block_test(target)
104 assert type(A) == EagerTensor, “Use only tensorflow and keras functions”
105 assert tuple(tf.shape(A).numpy()) == (3, 2, 2, 6), “Wrong shape.”
→ 106 assert np.allclose(A.numpy(), convolutional_block_output1), “Wrong values when training=False.”
107 print(A[0])
109 B = target(X, f = 2, filters = [2, 4, 6], training=True)

AssertionError: Wrong values when training=False.

2

You may send me your code of convolutional_block function in a private message. Click my name and message.

PS: I am a little busy today and will come back here after some 8 hours.

3

Ultimately, I had to ensure I was using all the right terms for each of the steps, including the skip step. You may need to scroll over a bit more to ensure that you are picking the right terms.