Tensor

创建

• Construct a 5x3 matrix, uninitialized：

x = torch.Tensor(5, 3)

• Construct a randomly initialized matrix

x = torch.rand(5, 3)

Operation

实现两个tensor的加法：x+y
1.

x + y

2.

torch.add(x, y)

3.giving an output tensor

result = torch.Tensor(5, 3)
torch.add(x, y, out=result)

4.in-place

y.add_(x)

Numpy Bridge

The torch Tensor and numpy array will share their underlying memory locations, and changing one will change the other.

Converting torch Tensor to numpy Array

a = torch.ones(5)
b = a.numpy()

Converting numpy Array to torch Tensor

a = np.ones(5)
b = torch.from_numpy(a)

CUDA Tensors

Tensors can be moved onto GPU using the .cuda function.

if torch.cuda.is_available():
    x = x.cuda()
    y = y.cuda()
    x + y

autograd.Variable

• .backward()
• .data
• .grad: autograd.Variable
• .creator: autograd.Function. Each variable has a .creator attribute that references a Function that has created the Variable (except for Variables created by the user - their creator is None).