The following defined function provides max pooling for the input 4D tensor tf.nn.max_pool:
max_pool( value, ksize, strides, padding, data_format='NHWC', name=None)
The preceding arguments are explained here:
- value: This is the 4D tensor with shape [batch, height, width, channels], type tf.float32 on which max pooling needs to be done.
- ksize: This is the list of ints that has length >= 4. The size of the window for each dimension of the input tensor.
- strides: This is the list of ints, length >= 4. A stride of the sliding window for each dimension of the input tensor.
- padding: This is a string, either VALID or SAME. The padding algorithm. The following section explains VALID and SAME padding.