|View source on GitHub|
Adds a 2D average pooling op.
tf.contrib.layers.avg_pool2d( inputs, kernel_size, stride=2, padding='VALID', data_format=DATA_FORMAT_NHWC, outputs_collections=None, scope=None )
It is assumed that the pooling is done per image but not in batch or channels.
inputs: A 4-D tensor of shape
[batch_size, height, width, channels]if
[batch_size, channels, height, width]if
kernel_size: A list of length 2: [kernel_height, kernel_width] of the pooling kernel over which the op is computed. Can be an int if both values are the same.
stride: A list of length 2: [stride_height, stride_width]. Can be an int if both strides are the same. Note that presently both strides must have the same value.
padding: The padding method, either 'VALID' or 'SAME'.
data_format: A string.
outputs_collections: The collections to which the outputs are added.
scope: Optional scope for name_scope.
Tensor representing the results of the pooling operation.