Week 2 Exercise 2

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning
1

Hi, I got the error message NameError: name ‘train_set_x’ is not defined. I tried again with the variable 'train_set_x_orig" but it returns the same name error. What should I do next?

2

Run all the above cells before running that particular cell.

3

Hi Saif, thanks for the prompt response. I did run the cells above.

4

And don’t change anything. Only write your code where it says
# WRITE YOUR CODE

5

Thanks, I re-ran the cells. Here’s the code I tried.

def flatten_dataset(X, num_px):
m = X.shape[0]
X_flatten = X.reshape(m, -1).T
return X_flatten / 255

num_px = train_set_x_orig.shape[1] # Assuming the images are square, i.e., num_px x num_px

train_set_x_flatten = flatten_dataset(train_set_x_orig, num_px)
test_set_x_flatten = flatten_dataset(test_set_x_orig, num_px)

print(“train_set_x_flatten shape:”, train_set_x_flatten.shape)
print(“test_set_x_flatten shape:”, test_set_x_flatten.shape)

The error message now - AssertionError: Wrong solution. Use (X.shape[0], -1).T.

6

Please share your full error (not code).

7

It seems like you are defining your own function flatten_dataset. You are making things complex for you. It is not mentioned anywhere to define your own function.

Anyways. Don’t need to divide by 255 now. It will be down in a separate cell. Moreover, you can make num_px = -1 or just remove it from your function.

But I prefer not to define your own function but just write code separately for:

# train_set_x_flatten = ...
# test_set_x_flatten = ...

And one more point, make sure you write all your code where it is mentioned # YOUR CODE STARTS HERE. Otherwise, grader will fail you.

Best,
Saif.