Course 4 Week 2 Assignment 1, convolutional_block "Wrong value"

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I can’t find what is wrong with my code. I keep getting the following message:
AssertionError Traceback (most recent call last)
in
13 assert type(A) == EagerTensor, “Use only tensorflow and keras functions”
14 assert tuple(tf.shape(A).numpy()) == (3, 2, 2, 6), “Wrong shape.”
—> 15 assert np.allclose(A.numpy(), convolutional_block_output1), “Wrong values when training=False.”
16 print(A[0])
17

AssertionError: Wrong values when training=False.

My code is below. Thanks!

{moderator edit - solution code removed}

2

I figure it out. The first Conv2D should have strides =(s, s), the second (1, 1)

3

It’s great to hear that you found the answer under your own power. This assignment is an excruciating exercise in proofreading (even more than normal programming assignments).

Just for future reference, we aren’t supposed to publish source code on the forums. I went ahead and removed it from your post. It sure helps for debugging sometimes, but we don’t want to leave it sitting out there for everyone to see.

4

Thanks! No more source code.