tf.math.reduce_mean | TensorFlow v2.16.1 (original) (raw)

tf.math.reduce_mean

Stay organized with collections Save and categorize content based on your preferences.

Computes the mean of elements across dimensions of a tensor.

View aliases

Main aliases

tf.math.reduce_mean(
    input_tensor, axis=None, keepdims=False, name=None
)

Used in the notebooks

Used in the guide	Used in the tutorials
Logistic regression for binary classification with Core APIs Multilayer perceptrons for digit recognition with Core APIs Distributed training with Core APIs and DTensor Quickstart for the TensorFlow Core APIs Introduction to gradients and automatic differentiation	Transfer learning with YAMNet for environmental sound classification Learned data compression Uncertainty-aware Deep Learning with SNGP CycleGAN Neural style transfer

Reduces input_tensor along the dimensions given in axis by computing the mean of elements across the dimensions in axis. Unless keepdims is true, the rank of the tensor is reduced by 1 for each of the entries in axis, which must be unique. If keepdims is true, the reduced dimensions are retained with length 1.

If axis is None, all dimensions are reduced, and a tensor with a single element is returned.

For example:

x = tf.constant([[1., 1.], [2., 2.]]) tf.reduce_mean(x) <tf.Tensor: shape=(), dtype=float32, numpy=1.5> tf.reduce_mean(x, 0) <tf.Tensor: shape=(2,), dtype=float32, numpy=array([1.5, 1.5], dtype=float32)> tf.reduce_mean(x, 1) <tf.Tensor: shape=(2,), dtype=float32, numpy=array([1., 2.], dtype=float32)>

Args
input_tensor	The tensor to reduce. Should have numeric type.
axis	The dimensions to reduce. If None (the default), reduces all dimensions. Must be in the range [-rank(input_tensor), rank(input_tensor)).
keepdims	If true, retains reduced dimensions with length 1.
name	A name for the operation (optional).

Returns
The reduced tensor.

numpy compatibility

Equivalent to np.mean

Please note that np.mean has a dtype parameter that could be used to specify the output type. By default this is dtype=float64. On the other hand, tf.reduce_mean has an aggressive type inference from input_tensor, for example:

x = tf.constant([1, 0, 1, 0]) tf.reduce_mean(x) <tf.Tensor: shape=(), dtype=int32, numpy=0> y = tf.constant([1., 0., 1., 0.]) tf.reduce_mean(y) <tf.Tensor: shape=(), dtype=float32, numpy=0.5>