TensorFlow学习笔记:tf.random_normal

最新推荐文章于 2021-10-08 00:28:10 发布

moon_skys

最新推荐文章于 2021-10-08 00:28:10 发布

阅读量699

点赞数

分类专栏：学习成长文章标签：学习

本文链接：https://blog.csdn.net/dengdengma520/article/details/79157733

版权

学习成长专栏收录该内容

19 篇文章 2 订阅

订阅专栏

该函数接受三个参数，分别是:

tf.random_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)

输出的数据呢，是服从标准正态分布的，shape是数据的形状(m*n的矩阵)，dtype是其类型。

这里的用法和np.random.normal(loc=0.0, scale=1.0, size=None)略像，

loc：Mean (“centre”) of the distribution

scale:Standard deviation (spread or “width”) of the distribution.

size : Output shape. If the given shape is, e.g., (m, n, k), then m * n * k samples are drawn. If size is None (default), a single value is returned if loc and scale are both scalars. Otherwise, np.broadcast(loc, scale).size samples are drawn.