tf.reduce_mean

最新推荐文章于 2022-03-28 20:26:24 发布

原创最新推荐文章于 2022-03-28 20:26:24 发布 · 1.3k 阅读

0 ·

CC 4.0 BY-SA版权

tensorflowandbiye 专栏收录该内容

4 篇文章

订阅专栏

本文详细介绍了TensorFlow中reduce_mean函数的功能及用法，包括如何计算张量各维度的平均值，以及函数参数说明。通过实例展示了不同参数设置下reduce_mean的计算结果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

reduce_mean(
    input_tensor,
    axis=None,
    keepdims=None,
    name=None,
    reduction_indices=None,
    keep_dims=None
)

Defined in tensorflow/python/ops/math_ops.py.

See the guide: Math > Reduction

Computes the mean of elements across dimensions of a tensor. (deprecated arguments)

SOME ARGUMENTS ARE DEPRECATED. They will be removed in a future version.Instructions for updating:keep_dims is deprecated, use keepdims instead

Reduces input_tensor along the dimensions given in axis.Unless keepdims is true, the rank of the tensor is reduced by 1 for eachentry in axis. If keepdims is true, the reduced dimensionsare retained with length 1.

If axis has no entries, all dimensions are reduced, and atensor with a single element is returned.

For example:

x = tf.constant([[1., 1.], [2., 2.]])
tf.reduce_mean(x)  # 1.5
tf.reduce_mean(x, 0)  # [1.5, 1.5]
tf.reduce_mean(x, 1)  # [1.,  2.]

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).
reduction_indices: The old (deprecated) name for axis.
keep_dims: Deprecated alias for keepdims.

Returns:

The reduced tensor.

Numpy Compatibility

Equivalent to np.mean

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

x = tf.constant([1, 0, 1, 0])
tf.reduce_mean(x)  # 0
y = tf.constant([1., 0., 1., 0.])
tf.reduce_mean(y)  # 0.5

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 3.0 License, and code samples are licensed under the Apache 2.0 License. For details, see our Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

上次更新日期：一月 27, 2018