Google的TensorFlow中的Theano Dimshuffle等效吗? [英] Theano Dimshuffle equivalent in Google's TensorFlow?

问题描述

我已经看到转置和重塑可以一起使用，但是我不知道如何使用.

I have seen that transpose and reshape together can help but I don't know how to use.

例如. dimshuffle(0，'x')

Eg. dimshuffle(0, 'x')

使用转置和整形等效于什么?或者，还有更好的方法? 谢谢.

What is its equivalent by using transpose and reshape? or is there a better way? Thank you.

推荐答案

在TensorFlow中实现Theano的dimshuffle的三个相关操作:

There are three relevant ops for implementing Theano's dimshuffle in TensorFlow:

• tf.transpose() 用于替换张量的尺寸.如果dimshuffle的参数中指定的模式是输入张量尺寸的排列(即没有'x'或缺少尺寸)，则可以使用tf.transpose()来实现dimshuffle().

• tf.transpose() is used to permute the dimensions of a tensor. If the pattern specified in the arguments to dimshuffle is a permutation of the input tensor's dimensions (i.e. there is no 'x' or missing dimension) you can use tf.transpose() to implement dimshuffle().

tf.expand_dims() 用于添加一个或更大的张量大小为1的尺寸.这可以处理将'x'指定为dimshuffle()模式的一部分的情况，但不会对现有尺寸重新排序.

tf.expand_dims() is used to add one or more size-1 dimensions to a tensor. This handles the case where 'x' is specified as part of the dimshuffle() pattern, but does not reorder the existing dimensions.

tf.squeeze() 用于删除一个或更多张量的size-1尺寸.这可以处理以下情况:从dimshuffle()模式中省略尺寸，但不对现有尺寸重新排序.

tf.squeeze() is used to remove one or more size-1 dimensions from a tensor. This handles the case where a dimension is omitted from a dimshuffle() pattern, but it does not reorder the existing dimensions.

假设输入是向量，则示例(dimshuffle(0, 'x'))只能使用tf.expand_dims()表示:

Assuming that the input is a vector, your example (dimshuffle(0, 'x')) can be expressed using tf.expand_dims() only:

input = tf.placeholder(tf.float32, [None])  # Defines an arbitrary-sized vector.
result = tf.expand_dims(input, 1)

print result.get_shape()  # ==> TensorShape([Dimension(None), Dimension(1)])

举一个更复杂的例子，将dimshuffle(1, 'x', 0)应用于矩阵将是:

Taking a more complicated example, dimshuffle(1, 'x', 0) applied to a matrix would be:

input = tf.placeholder(tf.float32, [128, 32])  # Defines a matrix.
output = tf.expand_dims(tf.transpose(input, [1, 0]), 1)

print output.get_shape()
# ==> TensorShape([Dimension(32), Dimension(1), Dimension(128)])

这篇关于Google的TensorFlow中的Theano Dimshuffle等效吗?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！