Residual network, week 2, CNN

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

###########input####################
def ResNet50(input_shape = (64, 64, 3), classes = 6):
…

####output###################################
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)
in
3 model = ResNet50(input_shape = (64, 64, 3), classes = 6)
4
----> 5 comparator(summary(model), ResNet50_summary)

~/work/release/W2A1/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

#########################################################

I can’t seem to find anything wrong with the code, so I dont understand the error.

2

I also got the same problem

1 Like
3

Hi noel9981,

This message indicates that you are using an operator instead of an Add() layer while constructing ResNet50. Have a look at the layers and see if you can locate where you do this. Good luck!

2 Likes
4

Hello Sir,

Thank you for the prompt reply.
Based on stated from the code cell, I’ve edited my code to include Add(), but the weirdest thing is, when I run the code and test it, the output I get, is the input_shape and a text box that lets me enter values, which makes no sense.

####input##############
model = ResNet50(input_shape = (64, 64, 3), classes = 6)
print(model.summary())
#####output##############
(64, 64, 3) (a textbox)
#####################

Is it possible for me to show you my code personally?

5

Hi noel9981,

Yes, that’s ok. You can send me your code using a direct message. I will then have a look.

6

i had the exact same issue, but I passed the earlier tests !! how is it possible?

7

Posting a new reply on a thread that’s been cold for four years, that is a bold strategy.

I recommend you start a new thread for your question, and include specific details on what “exact same issue” you are seeing.