I have passed over 80% of the exercises but unable to pass my work

Hi, I believe I have passed over 80% of the exercises but I am not able to pass as i keep getting 0/100. Cell 8 is the only place were i fail in exercise 1 - conv_block.

The pass mark is 65/100. There is an issue with your system that doesn’t allow many to get over the pass mark. I have followed the reading notes.

Please post a copy of any error messages or asserts in your notebook.

Hi Tom,

The error message happens in Exercise1 - conv_block function. First test passes second test fails.

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)


30 print(layer)


—> 32 comparator(summary(model2), output2)

/tf/W3A2/test_utils.py in comparator(learner, instructor)

17 “\n\n does not match the input value: \n\n”,

18 colored(f"{a}", “red”))

—> 19 raise AssertionError(“Error in test”)

20 print(colored(“All tests passed!”, “green”))


AssertionError: Error in test

Can you please help with a suggestion to resolve this?

When I submit my work i get 0/100 with error message: Cell #8. Can’t compile the student’s code. Error: AssertionError(‘Error in test’)

Please note every other exercise tests have passed

You didn’t mention which week number or assignment number you’re working on.

Tom, sorry about that. Here is the information you requested:
week 3
Image Segmentation with U-Net

This whole set of questions is strangely familiar, I just answered exactly the same situation on another thread.

Check that you’re using the “filters=n_filters” argument in both Conv2D layers. You also need to set the kernel_size, activation, padding, and kernel_initializer arguments.

1 Like

hi Tom,

I have set everything as per your instructions but I still get the same failure

Then you have some other error that I don’t understand.