Convolutional Neural Networks: Residual Networks (2 week, Prog.Assignment (1/2))

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Can’t pass test (3rd graded function). Please help.

Error: “AssertionError: Error in test”.

Test failed. Expected value:
“[‘Conv2D’, (None, 15, 15, 256), 16640, ‘valid’, ‘linear’, ‘RandomUniform’]
does not match the input value:
[‘Conv2D’, (None, 15, 15, 256), 16640, ‘same’, ‘linear’, ‘RandomUniform’]”

even if I change padding in: AveragePooling2D(pool_size=(2, 2), padding=‘valid’) to ‘same’ and vice-versa.

1 Like
2

Maybe an issue in your convolutional_block function? Since it adds some Conv2D layers as well…

2 Likes
3

You were right! Thank you! The error was higher in selecting “padding” even at the “identity_block” stage, rather than “convolutional_block”. I don’t understand how I passed the test on it XD

3 Likes