C4 W3 exercise 1 conv_block problem

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi, thanks for help.
There is an error in conv_block. Could anyone help me find it?

Block 1:
[‘InputLayer’, [(None, 96, 128, 3)], 0]
[‘Conv2D’, (None, 96, 128, 32), 896, ‘same’, ‘relu’, ‘HeNormal’]
[‘Conv2D’, (None, 96, 128, 32), 9248, ‘same’, ‘relu’, ‘HeNormal’]
[‘MaxPooling2D’, (None, 48, 64, 32), 0, (2, 2)]
All tests passed!

Block 2:
[‘InputLayer’, [(None, 96, 128, 3)], 0]
[‘Conv2D’, (None, 96, 128, 32), 896, ‘same’, ‘relu’, ‘HeNormal’]
[‘Conv2D’, (None, 96, 128, 32), 9248, ‘same’, ‘relu’, ‘HeNormal’]
[‘Dropout’, (None, 96, 128, 32), 0, 0.1]
[‘MaxPooling2D’, (None, 48, 64, 32), 0, (2, 2)]
Test failed
Expected value

[‘Conv2D’, (None, 96, 128, 1024), 28672, ‘same’, ‘relu’, ‘HeNormal’]

does not match the input value:

[‘Conv2D’, (None, 96, 128, 32), 896, ‘same’, ‘relu’, ‘HeNormal’]

AssertionError Traceback (most recent call last)
in
30 print(layer)
31
—> 32 comparator(summary(model2), output2)

/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

Thanks again

2

Please click my name and message your notebook as an attachment.

3

It looks like maybe you ignored the n_filters parameter and hard-coded the value. Hard-coding is never a good idea. The clue is that your Block 2 output is the same as for Block 1, but the parameters are different. So how could that happen? You must be ignoring the parameters.

4

Thanks for help

I found out the solution. I had a hard-coding problem, and set number of filters as 32, not n_filters.

Best regards,
Yizi