Week 3 Assignment 3 Unet Model Test Failed

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi,

I am getting the following message. Can you please help?

conv10 is Conv2D where the inputs are n_classes, kernel_size=1, padding=‘same’ times previous layer conv9

Test failed
Expected value

[‘Conv2D’, (None, 12, 16, 256), 295168, ‘same’, ‘relu’, ‘HeNormal’]

does not match the input value:

[‘Conv2D’, (None, 12, 16, 192), 221376, ‘same’, ‘relu’, ‘HeNormal’]

AssertionError Traceback (most recent call last)
in
5
6 unet = unet_model((img_height, img_width, num_channels))
----> 7 comparator(summary(unet), outputs.unet_model_output)

/tf/W3A2/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

2

I think you are looking in the wrong place. Note that the conv10 layer has n_classes as the number of filters and that is 23, right? The “expected” value is 256 for that layer and you have 192. I think you must have typed 6 someplace where you meant to type 8 (times n_filter).

3

Thank you Paulin! Indeed I wasn’t doubling the number of my filters in the contracting path up to 16.