突破Pytorch核心，Tensor ！！

import torch

# 创建一个标量
scalar_tensor = torch.tensor(3.14)

# 创建一个向量
vector_tensor = torch.tensor([1, 2, 3])

# 创建一个矩阵
matrix_tensor = torch.tensor([[1, 2, 3], [4, 5, 6]])

# 创建一个3D张量
tensor_3d = torch.rand((2, 3, 4))  # 2行3列4深度

# 获取张量的形状
shape = tensor_3d.shape

# 获取张量的数据类型
dtype = tensor_3d.dtype

# 获取张量所在的设备
device = tensor_3d.device

# 获取张量的形状
shape = tensor_3d.shape

# 改变张量的形状
reshaped_tensor = tensor_3d.view(3, 8)  # 将原始形状(2, 3, 4)变为(3, 8)

# 获取张量的存储
storage = tensor_3d.storage()

# 获取张量的形状
shape = tensor_3d.shape

# 获取张量的步幅
stride = tensor_3d.stride()

# 加法
result_add = tensor_3d + 2

# 乘法
result_mul = tensor_3d * 3

# 矩阵乘法
matrix_a = torch.rand((2, 3))
matrix_b = torch.rand((3, 4))
result_matmul = torch.mm(matrix_a, matrix_b)

# 大小比较
result_compare = tensor_3d > 0.5

# 逻辑运算
result_logical = torch.logical_and(result_add, result_compare)

# 索引
element = tensor_3d[0, 1, 2]

# 切片
sliced_tensor = tensor_3d[:, 1:3, :]

# 改变形状
reshaped_tensor = tensor_3d.view(3, 8)

# 转置
transposed_tensor = tensor_3d.transpose(0, 2)

# 广播
tensor_a = torch.rand((1, 3, 1))
tensor_b = torch.rand((2, 1, 4))
result_broadcast = tensor_a + tensor_b