I just started working with keras and noticed that there are two layers with very similar names for max-pooling:
MaxPooling. I was surprised that I couldn’t find the difference between these two on Google; so I am wondering what the difference is between the two if any.
They are the same… You can test it on your own
import numpy as np import tensorflow as tf from tensorflow.keras.layers import * # create dummy data X = np.random.uniform(0,1, (32,5,3)).astype(np.float32) pool1 = MaxPool1D()(X) pool2 = MaxPooling1D()(X) tf.reduce_all(pool1 == pool2) # True
1D max-pooling but the same is valid for all the pooling operations (2D, 3D, avg, global pooling)
Answered By – Marco Cerliani