Week 2 Assignment 1, Exercise 3--Resnet50 error

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I am getting the following error. I’m pretty sure I’m following the recommended code order, but I do not understand how the outputs are different.

Test failed 
 Expected value 

 ['Add', (None, 15, 15, 256), 0] 

 does not match the input value: 

 ['TensorFlowOpLayer', [(None, 15, 15, 256)], 0]
---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
<ipython-input-20-58a17f1e219d> in <module>
      3 model = ResNet50(input_shape = (64, 64, 3), classes = 6)
      4 
----> 5 comparator(summary(model), ResNet50_summary)

/tf/W2A1/test_utils.py in comparator(learner, instructor)
     21                   "\n\n does not match the input value: \n\n",
     22                   colored(f"{a}", "red"))
---> 23             raise AssertionError("Error in test")
     24     print(colored("All tests passed!", "green"))
     25 

AssertionError: Error in test
2

It looks like you must used a different function to do the addition operation than what the instructions told you to do. They give you an example in the instructions for the identity_block for how to do it and then that logic is actually part of the template code in convolutional_block. You can literally copy it from the second function.

3

I am facing the same issue and I just simply copied the command from the step 2 block :frowning:

4

@Chitoooo: Please show us the complete error output that you got as srkrish2 did earlier.

5

image
image997×677 59.8 KB

Thanks for your reply, this is the error that I got.

6

Ok, that is not the same error that srkrish reported. So there is something wrong with the way you are specifying the ReLU activation. It needs to be a Keras Layer function. I suggest you read the instructions again more carefully and scan around to see if the template code shows you any examples of ReLU.

7

Thank you for your help! Now my code works!

1 Like
8

That’s great! I’m glad to hear you found the solution.