Week 2 - Assignment 2

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

UNQ_C2

GRADED FUNCTION

def alpaca_model(image_shape=IMG_SIZE, data_augmentation=data_augmenter()):
‘’’ Define a tf.keras model for binary classification out of the MobileNetV2 model
Arguments:
image_shape – Image width and height
data_augmentation – data augmentation function
Returns:
Returns:
tf.keras.model
‘’’

I am getting errors as -

Test failed
Expected value

[‘Sequential’, (None, 160, 160, 3), 0]

does not match the input value:

[‘TensorFlowOpLayer’, [(None, 160, 160, 3)], 0]

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)
19 “\n\n does not match the input value: \n\n”,
20 colored(f"{a}", “red”))
—> 21 raise AssertionError(“Error in test”)
22 print(colored(“All tests passed!”, “green”))
23

AssertionError: Error in test

Can someone please, help me find my mistake?

2

The problem is in your MobileNetV2 layer. You’ve left a “None” statement there instead of specifying the input shape.

3

I changed that to this:

base_model = tf.keras.applications.MobileNetV2(input_shape=input_shape,
                                               include_top=False, # <== Important!!!!
                                               weights='imagenet') # From imageNet

Still getting the same error.

4

Data argument of preprocess input is wrong

5

Why it should be x? and not inputs?

6

Each output is the input to the next layer.
You got ‘x’ from data_augmentation() of the inputs.
Now you use ‘x’ in the next layer.
Then the later layers modify x in-place.

7

Thank’s for the explanation. It’s clear now.