- paddle.fluid.layers.nn. reduce_mean ( input, dim=None, keep_dim=False, name=None )
Computes the mean of the input tensor’s elements along the given dimension.
input (Variable) – The input variable which is a Tensor, the data type is float32, float64, int32, int64.
dim (list|int, optional) – The dimension along which the mean is computed. If None, compute the mean over all elements of
inputand return a variable with a single element, otherwise it must be in the range \([-rank(input), rank(input))\). If \(dim[i] < 0\), the dimension to reduce is \(rank(input) + dim[i]\).
keep_dim (bool, optional) – Whether to reserve the reduced dimension in the output Tensor. The result tensor will have one fewer dimension than the
keep_dimis true, default value is False.
name (str, optional) – The default value is None. Normally there is no need for user to set this property. For more information, please refer to Name
Tensor, results of average on the specified dim of input tensor, it’s data type is the same as input’s Tensor.
- Return type
TypeError, if out data type is different with the input data type. –
import paddle import paddle.fluid as fluid paddle.enable_static() # x is a Tensor variable with following elements: # [[0.2, 0.3, 0.5, 0.9] # [0.1, 0.2, 0.6, 0.7]] # Each example is followed by the corresponding output tensor. x = fluid.data(name='x', shape=[2, 4], dtype='float32') fluid.layers.reduce_mean(x) # [0.4375] fluid.layers.reduce_mean(x, dim=0) # [0.15, 0.25, 0.55, 0.8] fluid.layers.reduce_mean(x, dim=-1) # [0.475, 0.4] fluid.layers.reduce_mean(x, dim=1, keep_dim=True) # [[0.475], [0.4]] # y is a Tensor variable with shape [2, 2, 2] and elements as below: # [[[1.0, 2.0], [3.0, 4.0]], # [[5.0, 6.0], [7.0, 8.0]]] # Each example is followed by the corresponding output tensor. y = fluid.data(name='y', shape=[2, 2, 2], dtype='float32') fluid.layers.reduce_mean(y, dim=[1, 2]) # [2.5, 6.5] fluid.layers.reduce_mean(y, dim=[0, 1]) # [4.0, 5.0]