ConvNet Week2 Assignment ResNet50

Test failed
Expected value

[‘Conv2D’, (None, 15, 15, 64), 36928, ‘same’, ‘linear’, ‘RandomUniform’]

does not match the input value:

[‘Conv2D’, (None, 15, 15, 64), 36928, ‘same’, ‘linear’, ‘GlorotUniform’]

AssertionError Traceback (most recent call last)
3 model = ResNet50(input_shape = (64, 64, 3), classes = 6)
----> 5 comparator(summary(model), ResNet50_summary)

/tf/W2A1/ 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”))

AssertionError: Error in test

Have you compared the two layer specifications in detail? It is telling you that the initializer function is different on that Conv2D layer and that is why it is throwing the error. You are using “GlorotUniform” as the initializer, but they are expecting you to use “RandomUniform”.

Can you see how that happened?

One thing to note is that the instructions in the notebook use different random initializers in different cases. The random uniform initializer is only used in the identity block. For all the other cases, they specify GlorotUniform.