Pytorch 0.4 更新学习笔记

一.Tensor 和 Variable合并为Tensor。

    Tensor可以追踪计算图。所以没必要使用Variable了。

    type(x) -> x.type()

    使用detach()来获取Tensor的数值。

二.弃用volatile

    使用torch.no_grad()/torch.set_grad_enabled(grad_mode)来屏蔽计算图。

>>> x = torch.zeros(1, requires_grad=True)
>>> with torch.no_grad():
...     y = x * 2
>>> y.requires_grad
False
>>>
>>> is_train = False
>>> with torch.set_grad_enabled(is_train):
...     y = x * 2
>>> y.requires_grad
False

三.三个类torch.dtype/torch.device/torch.layout

    torch.dtype(使用Tensor的的dtype属性获取数据类型)

Data type	torch.dtype	Tensor types
32-bit floating point	torch.float32 or torch.float	torch.*.FloatTensor
64-bit floating point	torch.float64 or torch.double	torch.*.DoubleTensor
16-bit floating point	torch.float16 or torch.half	torch.*.HalfTensor
8-bit integer (unsigned)	torch.uint8	torch.*.ByteTensor
8-bit integer (signed)	torch.int8	torch.*.CharTensor
16-bit integer (signed)	torch.int16 or torch.short	torch.*.ShortTensor
32-bit integer (signed)	torch.int32 or torch.int	torch.*.IntTensor
64-bit integer (signed)	torch.int64 or torch.long	torch.*.LongTensor

    torch.device(使用Tensor的device属性获取Tensor的位置，cpu或gpu)

    torch.device('cpu')/torch.device('cuda')

    创建Tensor的方法

>>> device = torch.device("cuda:1")
>>> x = torch.randn(3, 3, dtype=torch.float64, device=device

>>> cuda = torch.device("cuda")
>>> torch.tensor([[1], [2], [3]], dtype=torch.half, device=cuda)

 >>> x = torch.randn(3, dtype=torch.float64)
 >>> torch.zeros_like(x)
 tensor([ 0.,  0.,  0.], dtype=torch.float64)

 >>> x = torch.randn(3, dtype=torch.float64)
 >>> x.new_ones(2)
 tensor([ 1.,  1.], dtype=torch.float64)

目前有用的是这些。其他的以后有需要再补充