Course 4 week 2 assignment 1 exercise 1 identity block

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi, I have submitted week 2 assignment 1, and my grade was 100/100. However, when I downloaded the code and then ran the code on my pc, I receive the following error which is related to the identity block:

AssertionError Traceback (most recent call last)
in
26 print(np.around(A4.numpy()[:,(0,-1),:,:].mean(axis = 3), 5))
27
—> 28 public_tests.identity_block_test(identity_block)

~\OneDrive - ------\Course\deepLearning AndrewNg\C4\W2A1-Residual Networks\public_tests.py in identity_block_test(target)
35 assert resume[1, 1, 0] - np.floor(resume[1, 1, 0]) > 0.7, “Looks like the BatchNormalization units are not working”
36
—> 37 assert np.allclose(resume,
38 np.array([[[ 0., 0., 0., 0., ],
39 [ 0., 0., 0., 0., ]],

AssertionError: Wrong values with training=False

and my code is as follows:

{Moderator edit: Code Removed}

I really appreciate it if anyone can guide me to solve this issue.

Many thanks!

2

Hello,

I deleted your code as it is against the community guide. In the future, please do not post your code.

Regarding your query, maybe your PC has a different version of Python, TensorFlow, and other libraries from the Coursera environment. Coursera use:

Python 3.8.10
TensorFlow 2.9.1

You can check yours by below code:

!python --version
import tensorflow as tf
print(f"TensorFlow {tf.__version__}")

BTW, on Google Colab, I can run this assignment with Python 3.10.11, TensorFlow 2.12.0

Best,
Saif.

3

Hello Saif,

Thank you very much for your reply and tips.
You are correct, the issue was related to Python and TensorFlow versions on my device.

Best regards,
Fatemeh

4

You may want to read this guide for virtual environment in your PC. Well, it is a little bit tricky, so, read Colab guide if you want to use it.