Course 2 Week 3 Assignment: forward_propagation function

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun
1

The following code is giving me the following error. I think it has something to do with the tf.function decorator, but I am not positive.

Z1 = tf.math.add(tf.linalg.matmul(W1, X), b1)
A1 = tf.keras.activations.relu(Z1)
Z2 = tf.math.add(tf.linalg.matmul(W2, X), b2)
A2 = tf.keras.activations.relu(Z2)
Z3 = tf.math.add(tf.linalg.matmul(W3, X), b3)

ValueError: Attempt to convert a value (<tensorflow.python.eager.def_function.Function object at 0x7f3aa834e710>) with an unsupported type (<class ‘tensorflow.python.eager.def_function.Function’>) to a Tensor.

2

Hi, @Cameron_Conroy.

There is an error in the expressions for Z2 and Z3. Can you spot it? Look at the comments in forward_propagation.

3

Hi @Cameron_Conroy. I am not sure about the source of this error. Can you provide a bit more code, specifically what you send on input as X? Also note that you might want to correct your usages of X as inputs in the code you attached

1 Like
4

I cannot spot the error. I couldn’t find anything in the comments

5

@yanivh gave you a good hint :slight_smile:

    #(approx. 5 lines)                   # Numpy Equivalents:
    # Z1 = ...                           # Z1 = np.dot(W1, X) + b1
    # A1 = ...                           # A1 = relu(Z1)
    # Z2 = ...                           # Z2 = np.dot(W2, A1) + b2
    # A2 = ...                           # A2 = relu(Z2)
    # Z3 = ...                           # Z3 = np.dot(W3, A2) + b3
6

It’s not the error I was expecting to see from that code :thinking:

7

I fixed it. Thanks for the pointer :slightly_smiling_face:

1 Like
8

Wonderful :slight_smile: Good luck with the rest of the assignment.

9

That’s what I wrote

YOUR CODE STARTS HERE

Z1 = tf.math.add(tf.linalg.matmul(W1, X), b1)
A1 = tf.keras.activations.relu(Z1)
Z2 = tf.math.add(tf.linalg.matmul(W2, A1), b2)
A2 = tf.keras.activations.relu(Z2)
Z3 = tf.math.add(tf.linalg.matmul(W3, A2), b3)

It runs well I guess, But after running the last cell this error comes up instead of
expected values:

NameError Traceback (most recent call last)
in
18 print("\033[92mAll test passed")
19
—> 20 forward_propagation_test(forward_propagation, new_train)

NameError: name ‘new_train’ is not defined

Where did I go wrong? Can you help ?

1 Like
10

I tried running the cells from top now its not showing error. Lol

1 Like
12

thank you for your guidance