Fix numpy broadcasting code

[denisshaf]

Hi James, thank you for your videos!

I fixed a mixed up lines in the last cell. You are trying to create x with an incorrect value of shape which is taken from the scope of the previous sells, and after that you assign a correct value to shape.

Before:

x = np.ones(shape, dtype=np.uint8) # for example
shape = (1000, 3, 32, 32)
out = np.empty(shape, dtype=np.uint8)

After:

shape = (1000, 3, 32, 32)
x = np.ones(shape, dtype=np.uint8) # for example
out = np.empty(shape, dtype=np.uint8)