Compute_Loss

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

{moderator edit - solution code removed}

I am getting error:
AssertionError: Test does not match. Did you get the reduce sum of your loss functions?

Can you plz assist me why I am getting this error

2

Which week of the course and which assignment is this from?

3

Assignment: Tensorflow Introduction
Weak: 3

4

There is no “compute_loss” function in that assignment.

5

It in “Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization” course

6

Do you mean the “compute_total_loss()” function?

7

Please post a screen capture image of the entire cell that contains the error message.

8

You have to transpose logits and labels. Check this.

9

I have transposed them but still having same error:

{moderator edit - solution code removed}

10

Instead of sharing your code, share your full error.

11

tf.Tensor(40.436035, shape=(), dtype=float32)

AssertionError Traceback (most recent call last)
in
17 print(“\033[92mAll test passed”)
18
—> 19 compute_total_loss_test(compute_total_loss, new_y_train )

in compute_total_loss_test(target, Y)
13 print(result)
14 assert(type(result) == EagerTensor), “Use the TensorFlow API”
—> 15 assert (np.abs(result - (0.50722074 + 1.1133534) / 2.0) < 1e-7), “Test does not match. Did you get the reduce sum of your loss functions?”
16
17 print(“\033[92mAll test passed”)

AssertionError: Test does not match. Did you get the reduce sum of your loss functions?

Expected output

tf.Tensor(0.810287, shape=(), dtype=float32)

12

Please check the definition of the loss function API. You are passing the arguments incorrectly.