It performs the average pooling on the input tensor. Each entry in the output is the mean of the corresponding size ksize window in value. It is defined using the tf.nn.avg_pool method:
avg_pool( value, ksize, strides, padding, data_format='NHWC', name=None)
Let's look at the code example where avg_pool is used in a simple 2D tensor:
import tensorflow as tfbatch_size=1input_height = 3input_width = 3input_channels = 1def main(): sess = tf.InteractiveSession() layer_input = tf.constant([ [ [[1.0], [0.2], [2.0]], [[0.1], [1.2], [1.4]], [[1.1], [0.4], [0.4]] ] ]) # The strides will look at the entire input by using the image_height and image_width kernel = [batch_size, input_height, input_width, input_channels] avg_pool = tf.nn.avg_pool(layer_input, ...