ConvNet Week2 resnet50

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi,
I get the following error in resnet50, (identity and convolutional block are ok):
I already varied the order in conv_block Add operation. Can some help

Test failed
Expected value

[‘Conv2D’, (None, 8, 8, 512), 66048, ‘valid’, ‘linear’, ‘GlorotUniform’]

does not match the input value:

[‘Conv2D’, (None, 8, 8, 256), 33024, ‘valid’, ‘linear’, ‘GlorotUniform’]

AssertionError Traceback (most recent call last)
in
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 the filters in the Conv2D layer are incorrect.
Perhaps there is an error in your convolutional_block() function.
Did you hard-code some values there that shouldn’t be? You should use the F1, F2, and F3 values for the filters.

3

Thanks for the immidiate hint.
Convolutional_block ends with same values as expected. I used F2 and F3, and no other hardcodes as described like kernel_size = (1, 1), strides=(1,1).
Maybe a stupid error, but I couldnt find it.

tf.Tensor(
[[[0. 0.66683817 0. 0. 0.88853896 0.5274254 ]
[0. 0.65053666 0. 0. 0.89592844 0.49965227]]

[[0. 0.6312079 0. 0. 0.8636247 0.47643146]
[0. 0.5688321 0. 0. 0.85534114 0.41709304]]], shape=(2, 2, 6), dtype=float32)
All tests passed!