Course 4 Week 2, Assigment 1- Exercise 2 - convolutional_block

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hello,
I have these AssertionError: Wrong values when training=True in convolutional block exercise
I’m unable to find my mistake.

I already review:
a) Hyperparameters (they are OK- same values as indicated in the exercise)
b) I’m using X_shortcut in shortcut path

Can anyone give me some advice about how to figure out it?

This is my output when I executed the validation code:

tf.Tensor(
[[[0. 0.66683817 0. 0. 0.88853896 0.5274254 ]
[0. 0.65053666 0. 0. 0.89592844 0.49965227]]

[[0. 0.6312079 0. 0. 0.8636247 0.47643146]
[0. 0.5688321 0. 0. 0.85534114 0.41709304]]], shape=(2, 2, 6), dtype=float32)

AssertionError Traceback (most recent call last)
in
16
17 B = convolutional_block(X, f = 2, filters = [2, 4, 6], training=True)
—> 18 assert np.allclose(B.numpy(), convolutional_block_output2), “Wrong values when training=True.”
19
20 print(’\033[92mAll tests passed!’)

AssertionError: Wrong values when training=True.

2

Hey @ErikaRamos , could you share your notebook with me in a direct message ? I could then help you with it. Thanks.

3

Hello @Mubsi,

I have exactly the same error. My output is the same as the expected output, but it is raising the error ‘‘AssertionError: Wrong values when training=True.’’ How can I handle it?

4

Hi @Javokhir_Khusanov,

Can you share your lab ID with me ? In the assignment, when you click the top right “Help” button, a panel will open and your lab ID will be shown at the bottom.

I shall take a look.

Thanks,
Mubsi

5

@Mubsi

sure, here we are:
sykqcbqf

6

Heyy Mubsi !!!
Are you there ? I posted id here ? Can we solve the problem ?