TensorFlow:生成一个随机常数 [英] TensorFlow: generating a random constant

问题描述

在ipython中，我导入了tensorflow as tf和numpy as np并创建了一个TensorFlow InteractiveSession. 当我使用numpy输入运行或初始化一些正态分布时，一切运行正常:

In ipython I imported tensorflow as tf and numpy as np and created an TensorFlow InteractiveSession. When I am running or initializing some normal distribution with numpy input, everything runs fine:

some_test = tf.constant(np.random.normal(loc=0.0, scale=1.0, size=(2, 2)))
session.run(some_test)

返回:

array([[-0.04152317,  0.19786302],
       [-0.68232622, -0.23439092]])

正如预期的那样.

...但是当我使用Tensorflow正态分布函数时:

...but when I use the Tensorflow normal distribution function:

some_test = tf.constant(tf.random_normal([2, 2], mean=0.0, stddev=1.0, dtype=tf.float32))
session.run(some_test)

...它引发类型错误，提示:

...it raises a Type error saying:

(...)
TypeError: List of Tensors when single Tensor expected

我在这里想念什么?

输出:

sess.run(tf.random_normal([2, 2], mean=0.0, stddev=1.0, dtype=tf.float32))

单独返回与np.random.normal生成的->形状为(2, 2)的矩阵完全相同的东西，其值取自正态分布.

alone returns the exact same thing which np.random.normal generates -> a matrix of shape (2, 2) with values taken from a normal distribution.

推荐答案

tf.constant() op接受一个numpy数组(或可隐式转换为numpy数组的东西)，并返回另一方面，tf.random_normal() op返回一个tf.Tensor，其值每次运行时都会根据给定的分布随机生成.由于它返回tf.Tensor，因此不能用作tf.constant()的参数.解释了TypeError(与tf.InteractiveSession的使用无关，因为它是在构建图形时出现的.)

On the other hand, the tf.random_normal() op returns a tf.Tensor whose value is generated randomly according to the given distribution each time it runs. Since it returns a tf.Tensor, it cannot be used as the argument to tf.constant(). This explains the TypeError (which is unrelated to the use of tf.InteractiveSession, since it occurs when you build the graph).

我假设您希望图形包含一个张量，该张量(i)在首次使用时随机生成，并且(ii)此后是常数.有两种方法可以做到这一点:

I'm assuming you want your graph to include a tensor that (i) is randomly generated on its first use, and (ii) constant thereafter. There are two ways to do this:

1. 使用NumPy生成随机值，并将其放入tf.constant()中，就像您在问题中所做的那样:

1. Use NumPy to generate the random value and put it in a tf.constant(), as you did in your question:

some_test = tf.constant(
    np.random.normal(loc=0.0, scale=1.0, size=(2, 2)).astype(np.float32))

(可能更快，因为它可以使用GPU生成随机数)使用TensorFlow生成随机值并将其放入tf.Variable:

some_test = tf.Variable(
    tf.random_normal([2, 2], mean=0.0, stddev=1.0, dtype=tf.float32)
sess.run(some_test.initializer)  # Must run this before using `some_test`

这篇关于TensorFlow:生成一个随机常数的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！