Course 4 Week 1 Assignment 1 - Exercise 5 conv_backward()

tangw · August 13, 2021, 9:18pm

I have a question regarding the final output of dW and db. In the code, we take the sum of dW, db across all m training examples. I’m wondering if we need to divide them by number of training example m in the end? In the standard NN we implemented before, I remember we always divide dW and db by m.

Thanks,
Weijia

carlosrl · April 21, 2022, 7:16pm

Hi @tangw Do you still need help with this?

Topic		Replies	Views
Backpropagation in Convolutional Neural Networks - dW overall derivative Convolutional Neural Networks	2	542	August 24, 2022
C4_W1_A1 dW and db calculation question Convolutional Neural Networks	4	520	March 9, 2023
2 layer model Week4 exercise 1 Neural Networks and Deep Learning	1	484	July 11, 2022
Convolutional Neural Networks, Week 1, conv_backward Convolutional Neural Networks	2	656	January 22, 2022
Course 1 Week2 Assignment - Excercise 5 Neural Networks and Deep Learning	2	549	July 6, 2021

Course 4 Week 1 Assignment 1 - Exercise 5 conv_backward()

Related topics