Reduction
TensorFlow provides several operations that you can use to perform common math computations that reduce various dimensions of a tensor.
沿着某个方向（reduction_indices）降维
tf.reduce_sum
tf.reduce_prod
tf.reduce_min
tf.reduce_max
tf.reduce_mean
tf.reduce_all
tf.reduce_any
tf.reduce_logsumexp
tf.count_nonzero
tf.accumulate_n
tf.einsum
参考资料链接：https://github.com/tensorflow/docs/blob/8c01fda9b4debce8e9e2acc266c758090a14080a/site/en/api_guides/python/math_ops.md#reduction
具体说明文档
tf.reduce_mean(
input_tensor,
axis=None,
keepdims=None,
name=None,
reduction_indices=None,
keep_dims=None
)
参考资料链接：
https://tensorflow.google.cn/api_docs/python/tf/reduce_mean