Exercise 2 - convolutional_block

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi all,
I am getting the below error? can anyone help me please?

AssertionError                            Traceback (most recent call last)
<ipython-input-5-869d2d1d4c16> in <module>
     12 assert type(A) == EagerTensor, "Use only tensorflow and keras functions"
     13 assert tuple(tf.shape(A).numpy()) == (3, 2, 2, 6), "Wrong shape."
---> 14 assert np.allclose(A.numpy(), convolutional_block_output1), "Wrong values when training=False."
     15 print(A[0])
     16 

AssertionError: Wrong values when training=False.
2

I found out the problem. I defined X_shortcut wrongly

3

Great! I hope this fixed your other later problem with resnet50. So it was the convolutional_block that was wrong. There’s a lesson here about not looking at the output of the earlier cells in the notebook. :thinking:

1 Like
4

Thanks Paul,
you are a great asset for deeplearning courses.

1 Like