Course 4 Week 2 Assignment 2 Exercise 2 error

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

This is the error I keep getting in Exercise 2 of the 2nd assignment of week 2:

AssertionError Traceback (most recent call last)
in
10 [‘Dense’, (None, 1), 1281, ‘linear’]] #linear is the default activation
11
—> 12 comparator(summary(model2), alpaca_summary)
13
14 for layer in summary(model2):

~/work/W2A2/test_utils.py in comparator(learner, instructor)
14 def comparator(learner, instructor):
15 if len(learner) != len(instructor):
—> 16 raise AssertionError(f"The number of layers in the model is incorrect. Expected: {len(instructor)} Found: {len(learner)}")
17 for a, b in zip(learner, instructor):
18 if tuple(a) != tuple(b):

AssertionError: The number of layers in the model is incorrect. Expected: 8 Found: 7

I have no idea what I’m doing wrong. Am I missing an entire layer?

This is the code I’ve written for that block:

# UNQ_C2
# GRADED FUNCTION
def alpaca_model(image_shape=IMG_SIZE, 
# mentor edit: code removed
2

Please refrain from sharing your code publicly on the forum. This is against our Code of Conduct. If a mentor requires access to your code to assist you, they will reach out to you directly via a private message

image
Hint:
You need to provide a function argument here.

1 Like
3

Sorry about posting the code, and thank you for your reply! I tried adding x=data_augmentation(inputs), and it still gives the same error.

Side question, when data_augmentation (or rather data_augmenter, the function) was defined, it didn’t take any functional argument, so why would it need one here?

4

In the markup below, at “A” you put “inputs”.
This gives you ‘x’.
Then you use preprocess ‘x’ and get a new ‘x’.

image

This code in the function definition:
image

… gives you data_augmentation as a function pointer. You still have to give it some data to operate on.

1 Like
5

That fixed it. Thank you so much!

1 Like