PyTorch一小时掌握之基本操作篇

torch.empty(*size, *, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False, pin_memory=False, memory_format=torch.contiguous_format) → Tensor

# 创建一个形状为[2, 2]的矩阵
a = torch.empty(2, 2)
print(a)

# 创建一个形状为[3, 3]的矩阵
b = torch.empty(3, 3)
print(b)

torch.zeros(*size, *, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) → Tensor

# 创建一个形状为[2, 2]的全零数组
a = torch.zeros([2, 2], dtype=torch.float32)
print(a)

# 创建一个形状为[3, 3]的全零数组
b = torch.zeros([3, 3], dtype=torch.float32)
print(b)

torch.ones(*size, *, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) → Tensor

# 创建一个形状为[2, 2]的全一数组
a = torch.ones([2, 2], dtype=torch.float32)
print(a)

# 创建一个形状为[3, 3]的全一数组
b = torch.ones([3, 3], dtype=torch.float32)
print(b)

torch.tensor(data, *, dtype=None, device=None, requires_grad=False, pin_memory=False) → Tensor

# 通过数据创建张量
array = np.arange(1, 10).reshape(3, 3)
print(array)
print(type(array))

tensor = torch.tensor(array)
print(tensor)
print(type(tensor))

torch.rand(*size, *, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) → Tensor

# 创建形状为[2, 2]的随机数矩阵
rand = torch.rand(2, 2)
print(rand)

torch.add(input, other, *, out=None) → Tensor

# 张量相加
input1 = torch.tensor([[1, 2], [3, 4]])
print(input1)

input2 = torch.tensor([[4, 3], [2, 1]])
print(input2)

output = torch.add(input1, input2)
print(output)

# 张量相减
input1 = torch.tensor([[1, 2], [3, 4]])
print(input1)

input2 = torch.tensor([[4, 3], [2, 1]])
print(input2)

output = torch.sub(input1, input2)
print(output)

# 张量矩阵相乘
input1 = torch.tensor([[1, 1, 1]])
print(input1)

input2 = torch.tensor([[3], [3], [3]])
print(input2)

output = torch.matmul(input1, input2)
print(output)

# 简单的索引操作
ones = torch.ones([3, 3])
print(ones[: 2])
print(ones[:, : 2])