Week2 Exercise 2 - convolutional_block

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

AssertionError Traceback (most recent call last)
in
12 assert type(A) == EagerTensor, “Use only tensorflow and keras functions”
13 assert tuple(tf.shape(A).numpy()) == (3, 2, 2, 6), “Wrong shape.”
—> 14 assert np.allclose(A.numpy(), convolutional_block_output1), “Wrong values when training=False.”
15 print(A[0])
16

AssertionError: Wrong values when training=False.

2

Please click my name and message your code for def identity_block.

3

@Lucy_Hui

Thanks for the code.

Here are some hints:

  1. There is no variable s inside the function identity_block
  2. See if Conv2D layer can be provided the trainable argument.
  3. strides parameter should be set to the right values for conv layers.
  4. Your understanding of X_shortcut is wrong.

Please watch the lectures and read the markdown for the assignment before moving forward.

4

sorry i can’t understand you , there is no any identity_block in my code

5

No worries. I’m referring to this function:
def identity_block(X, f, filters, training=True, initializer=random_uniform):

6

I asked @Lucy_Hui to create a new post. Instead, this post was changed by Lucy from identity_block to convolutional_block.