DLS C4W2 Error: "Looks like the BatchNormalization units are not working"

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hello everyone.
I was trying to do DLS C4W2 assignment, and I have been stuck on this for too long. I have even seen many solutions online and still can’t get it right.
image

2

You are using an older version of the notebook.
Here’s the new function signature:

# UNQ_C1
# GRADED FUNCTION: identity_block

def identity_block(X, f, filters, initializer=random_uniform):

Please follow these steps to refresh your workspace

Posting solution code in a public topic is discouraged and can get your account suspended. It’s okay to share stacktrace on a public post and send code to a mentor via direct message. Don’t forget to clean up the post.

3

Please explain why you are setting the training parameter only for BatchNormalization. The test code explicitly manages the learning state via tf.keras.backend.set_learning_phase(True) and tf.keras.backend.set_learning_phase(False)

4

Sorry sir. Must’ve been a brain-fade moment from my side.
Thank you so much. All my doubts have been solved and I’ve successfully completed the assignment.