theano dimshuffle的使用说明

最新推荐文章于 2017-08-21 10:01:05 发布

原创最新推荐文章于 2017-08-21 10:01:05 发布 · 313 阅读

0 ·

CC 4.0 BY-SA版权

Python 专栏收录该内容

8 篇文章

订阅专栏

本文详细介绍了如何使用特定模式对张量进行维度变换，包括如何使用‘x’字符来进行广播操作，并提供了多个实例来帮助理解不同模式的效果。

Returns a view of this tensor with permuted dimensions. Typically the pattern will include the integers 0, 1, ... ndim-1, and any number of‘x’ characters in dimensions where this tensor should be broadcasted.

A few examples of patterns and their effect:

(‘x’) -> make a 0d (scalar) into a 1d vector
(0, 1) -> identity for 2d vectors
(1, 0) -> inverts the first and second dimensions
(‘x’, 0) -> make a row out of a 1d vector (N to 1xN)
(0, ‘x’) -> make a column out of a 1d vector (N to Nx1)
(2, 0, 1) -> AxBxC to CxAxB
(0, ‘x’, 1) -> AxB to Ax1xB
(1, ‘x’, 0) -> AxB to Bx1xA
(1,) -> This remove dimensions 0. It must be a broadcastable dimension (1xA to A)

变换的时候数字分别代表维度,x类似于reshpe中的-1参数,最后分配.