具有可变大小的张量流常数 [英] tensorflow constant with variable size

问题描述

我有一个可变的批量大小，所以我所有的输入都是这样的

I have a variable batch size, so all of my inputs are of the form

tf.placeholder(tf.float32, shape=(None, ...)

接受可变批量大小.但是，您如何创建具有可变批量大小的常量值?问题出在这一行:

to accept the variable batch sizes. However, how might you create a constant value with variable batch size? The issue is with this line:

log_probs = tf.constant(0.0, dtype=tf.float32, shape=[None, 1])

它给了我一个错误:

TypeError: unsupported operand type(s) for *: 'NoneType' and 'int'

我确信可以用可变批量大小初始化一个常量张量，我该怎么做?

I'm sure it is possible to initialize a constant tensor with variable batch size, how might I do so?

我还尝试了以下方法:

tf.constant(0.0, dtype=tf.float32, shape=[-1, 1])

我收到此错误:

ValueError: Too many elements provided. Needed at most -1, but received 1

推荐答案

A tf.constant() 在图形构建时具有固定的大小和值，因此它可能不适合您的应用程序.

A tf.constant() has fixed size and value at graph construction time, so it probably isn't the right op for your application.

如果您尝试为每个元素创建一个具有动态大小和相同(常量)值的张量，您可以使用 tf.fill() 和 tf.shape() 以创建适当形状的张量.例如，要创建一个与 input 具有相同形状且值 0.5 的张量 t:

If you are trying to create a tensor with a dynamic size and the same (constant) value for every element, you can use tf.fill() and tf.shape() to create an appropriately-shaped tensor. For example, to create a tensor t that has the same shape as input and the value 0.5 everywhere:

input = tf.placeholder(tf.float32, shape=(None, ...))

# `tf.shape(input)` takes the dynamic shape of `input`.
t = tf.fill(tf.shape(input), 0.5)

正如 Yaroslav 在他的评论中提到的，您也可以使用 (NumPy-style) 广播 来避免实现具有动态形状的张量.例如，如果 input 的形状为 (None, 32) 而 t 的形状为 (1, 32) 那么计算 tf.mul(input, t) 将在第一维上广播 t 以匹配 input 的形状.

As Yaroslav mentions in his comment, you may also be able to use (NumPy-style) broadcasting to avoid materializing a tensor with dynamic shape. For example, if input has shape (None, 32) and t has shape (1, 32) then computing tf.mul(input, t) will broadcast t on the first dimension to match the shape of input.

这篇关于具有可变大小的张量流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！