60min入门pytorch节选

1. torch简单创建

shape = (2,3,)
rand_tensor = torch.rand(shape)
ones_tensor = torch.ones(shape)
zeros_tensor = torch.zeros(shape)

print(f"Random Tensor: \n {rand_tensor} \n")
print(f"Ones Tensor: \n {ones_tensor} \n")
print(f"Zeros Tensor: \n {zeros_tensor}")

2. torch和numpy转换

import torch
import numpy as np
data = [[1, 2], [3, 4]]
x_data = torch.tensor(data)
np_array = np.array(data)
x_np = torch.from_numpy(np_array)
x_np.numpy()

3. 创建相似维度Tensor

x_ones = torch.ones_like(x_data)   # 保留 x_data 的属性: 结构 类型，也可以指定类型
print(f"Ones Tensor: \n {x_ones} \n")

x_rand = torch.rand_like(x_data, dtype=torch.float)   # 重写 x_data 的数据类型 int -> float
print(f"Random Tensor: \n {x_rand} \n")

4. Tensor的基本属性

tensor = torch.rand(3,4)

print(f"Shape of tensor: {tensor.shape}")
print(f"Datatype of tensor: {tensor.dtype}")
print(f"Device tensor is stored on: {tensor.device}")

5. 查看GPU可获取

# 判断当前环境GPU是否可用, 然后将tensor导入GPU内运行
if torch.cuda.is_available():
  tensor = tensor.to('cuda')

6. 张量拼接

tensor = torch.ones(4, 4)
t1 = torch.cat([tensor, tensor, tensor], dim=1) # dim == 1 则是横向加，维度变成4*12
print(t1)

7. 张量乘积（对应位置相乘：mul 和 *）

# 逐个元素相乘结果
print(f"tensor.mul(tensor): \n {tensor.mul(tensor)} \n")
# 等价写法:
print(f"tensor * tensor: \n {tensor * tensor}")
# 即为 mul 和 *

8. 张量矩阵乘法（matmul 和 @）

print(f"tensor.matmul(tensor.T): \n {tensor.matmul(tensor.T)} \n")
# 等价写法:
print(f"tensor @ tensor.T: \n {tensor @ tensor.T}")
# 即为multal 和 @