pytorch官方教程学习笔记01：WHAT IS PYTORCH?

官网

1.创建张量：大小为5行3列：

whatever values were in the allocated memory at the time will appear as the initial values.

x = torch.empty(5, 3)

随机初始化：

x = torch.rand(5, 3)

全零+指定类型：

x = torch.zeros(5, 3, dtype=torch.long)

**自定义初始化：需要用到：【】 **

x = torch.tensor([[1, 2], [3, 4]])

输出大小：

print(x.size())

2.运算：

torch.add(x, y, out=result)
print(result)

直接加到y上了。

y.add_(x)
print(y)

3.改变维度：

x = torch.randn(4, 4)
y = x.view(16)
z = x.view(-1, 8)  # the size -1 is inferred from other dimensions
print(x.size(), y.size(), z.size())

这里的-1 设计的很妙啊！

4.item（）：只适用于1行1列的tensor变为一个 Python number。

x = torch.randn(1)
print(x)
print(x.item())

5.与numpy进行类型互转：

Converting a Torch Tensor to a NumPy Array：

b = a.numpy()

Converting NumPy Array to Torch Tensor：

b = torch.from_numpy(a)

6.最后，但是是最重要的一点：CUDA GPU 相关，用一个.to（设备），将其转化为特定设备上的类型。默认cpu。：

Tensors can be moved onto any device using the .to method.

# let us run this cell only if CUDA is available
# We will use ``torch.device`` objects to move tensors in and out of GPU
if torch.cuda.is_available():
    device = torch.device("cuda")          # a CUDA device object
    y = torch.ones_like(x, device=device)  # directly create a tensor on GPU
    x = x.to(device)                       # or just use strings ``.to("cuda")``
    z = x + y
    print(z)
    print(z.to("cpu", torch.double))       # ``.to`` can also change dtype together!