.data在pytorch中仍然有用吗?

本文介绍了.data在pytorch中仍然有用吗?的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！ 问题描述

我是pytorch的新手.我读了很多pytorch代码，这些代码大量使用了张量的.data成员.但是我在官方文档和Google中搜索.data，却发现很少.我想.data包含张量中的数据，但我不知道何时需要它，何时不需要它?

I'm new to pytorch. I read much pytorch code which heavily uses tensor's .data member. But I search .data in the official document and Google, finding little. I guess .data contains the data in the tensor, but I don't know when we need it and when not?

推荐答案

.data是Variable的属性(对象表示Tensor具有历史跟踪功能，例如用于自动更新)，而不是Tensor.实际上，.data允许访问Variable的基础Tensor.

.data was an attribute of Variable (object representing Tensor with history tracking e.g. for automatic update), not Tensor. Actually, .data was giving access to the Variable's underlying Tensor.

但是，由于PyTorch版本0.4.0，Variable和Tensor已被合并(成为更新的Tensor结构)，所以.data沿着先前的Variable对象消失了(Variable是仍然具有向后兼容性，但已弃用).

However, since PyTorch version 0.4.0, Variable and Tensor have been merged (into an updated Tensor structure), so .data disappeared along the previous Variable object (well Variable is still there for backward-compatibility, but is deprecated).

来自版本0.4.0的发行说明的段落(我建议阅读有关Variable/Tensor更新的整个部分):

Paragraph from Release Notes for version 0.4.0 (I recommend reading the whole section about Variable/Tensor updates):

.data怎么样?

What about .data?

.data是从计算机获取基础Tensor的主要方法 Variable.合并之后，调用y = x.data仍然具有类似的功能 语义.因此，y将是与以下对象共享相同数据的Tensor x，与x的计算历史无关，并且具有 requires_grad=False.

.data was the primary way to get the underlying Tensor from a Variable. After this merge, calling y = x.data still has similar semantics. So y will be a Tensor that shares the same data with x, is unrelated with the computation history of x, and has requires_grad=False.

但是，在某些情况下.data可能是不安全的. x.data上的任何更改 不会被autograd跟踪，并且计算出的梯度将是 如果在向后传递中需要x，则不正确.一个更安全的选择是 使用x.detach()，它还会返回共享数据的Tensor 与requires_grad=False一起使用，但会就地更改 如果后向需要x，则由autograd报告.

However, .data can be unsafe in some cases. Any changes on x.data wouldn't be tracked by autograd, and the computed gradients would be incorrect if x is needed in a backward pass. A safer alternative is to use x.detach(), which also returns a Tensor that shares data with requires_grad=False, but will have its in-place changes reported by autograd if x is needed in backward.