Course 1, Week 1, assignment conv_single_step

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi,

I have a question regarding, the assignment, where you have to compute a single step of convolution. In the exercise you have to cast the result of an array with only one element as a float. I tried different ways of casting to float, but it always returns the error, that I need to cast to float (see image). When I check the data type it shows that it is class float (see image). What am I doing wrong? Or am I casting to a wrong float?

Thanks

image
image1018×462 26.3 KB

2

Hi @Roman_Fabrik
You just need to follow the comments. Anyway, to help you understand what to do, you can do a debug, printing the types of Z and b. So, add this line to your code
print(type(Z), type(b))
This will help you understand what is going on and how to correctly complete the code.
Keep learning!

3

Here is the comment from the notebook:

# Add bias b to Z. Cast b to a float() so that Z results in a scalar value.

Only cast b as a float and the Z will be in scalar automatically. And, after making the changes, you have to run the cell again to update the changes.

4

Thank you for the help, after reloading the kernel it suddenly worked.