对tf.reduce_mean API的理解就是求平均值，reduce指的是一串数据求平均值后维数降低了，可不是吗，一串向量变成了一个数，维数自然降低了

最新推荐文章于 2022-04-19 20:42:15 发布

原创最新推荐文章于 2022-04-19 20:42:15 发布 · 228 阅读

0 ·

CC 4.0 BY-SA版权

tensorflow 专栏收录该内容

77 篇文章

订阅专栏

本文详细解析了TensorFlow中的tf.reduce_mean函数，解释了如何通过该函数对输入张量进行平均值计算，包括参数说明、使用场景及示例代码。了解tf.reduce_mean在不同维度上的操作方式，掌握其在神经网络训练、自定义层和模型等领域的应用。

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

对tf.reduce_mean的理解就是求平均值，reduce指的是一串数据求平均值后维数降低了，可不是吗，一串向量变成了一个数，维数自然降低了

API URL

https://tensorflow.google.cn/api_docs/python/tf/math/reduce_mean?hl=en

Used in the notebooks

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

Used in the notebooks

Used in the guide	Used in the tutorials
Training checkpoints Writing custom layers and models with Keras Ragged tensors Eager execution Better performance with tf.function and AutoGraph	CycleGAN Neural style transfer Custom training: basics Convolutional Variational Autoencoder DeepDream

Reduces input_tensor along the dimensions given in axis. Unless keepdims is true, the rank of the tensor is reduced by 1 for each entry in axis. 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)  # 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).

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

Reduces input_tensor along the dimensions given in axis