Hi, my understanding is that when padding=‘same’ for tf.keras.layers.MaxPooling2D, the input and output shape should be the same. For example in week1 assignment 2, P1 = tfl.MaxPool2D(pool_size=(8, 8), strides=(8, 8), padding=‘same’)(A1) , if input shape is (64, 64, 8), the output shape should still…

tf.keras.layers.MaxPooling2D with padding='same'

TMosh October 10, 2023, 3:06am 2

This thread might be helpful.

Topic		Replies	Views
C4 W1 A2 MaxPooling2D Convolutional Neural Networks coursera-platform	6	471	September 29, 2023
W1A2: Output size for tfl.MaxPooling2D with argument: padding='same' Convolutional Neural Networks week-1 , coursera-platform	2	241	March 16, 2024
Course 4 Week 1 Assignment-2 Functional API Maxpool2D Convolutional Neural Networks coursera-platform	1	625	September 24, 2021
Convolution_model_Application - MaxPooling Padding Question Convolutional Neural Networks coursera-platform	3	591	March 2, 2024
Week 1 - Assignment 2 - Exercise - Unnecessary padding Convolutional Neural Networks coursera-platform	1	598	November 22, 2022