数据操作
1 import torch 2 3 torch.manual_seed(0) 4 torch.cuda.manual_seed(0) 5 print(torch.__version__) # 1.3.1
创建tensor
1 # 创建一个5x3的未初始化的tensor 2 x = torch.empty(5, 3) 3 print(x) 4 5 # tensor([[1.3563e-19, 1.3563e-19, 7.9717e-10], 6 # [5.8270e-10, 5.8270e-10, 4.9153e-14], 7 # [1.3563e-19, 1.8578e-01, 3.9157e-02], 8 # [4.7429e+30, 2.2639e+35, 1.8971e+31], 9 # [1.4587e-19, 1.1703e-19, 1.5637e-01]])
# 随机初始化的tensor x = torch.rand(5, 3) print(x)
# tensor([[0.4963, 0.7682, 0.0885], # [0.1320, 0.3074, 0.6341], # [0.4901, 0.8964, 0.4556], # [0.6323, 0.3489, 0.4017], # [0.0223, 0.1689, 0.2939]])
# 创建一个long型全0的tensor x = torch.zeros(5, 3, dtype=torch.long) print(x)
# tensor([[0, 0, 0], # [0, 0, 0], # [0, 0, 0], # [0, 0, 0], # [0, 0, 0]])
# 直接数据初始化 x = torch.tensor([5.5, 3]) print(x)
# tensor([5.5000, 3.0000])
# 通过现有的tensor来创建 x = x.new_ones(5, 3, dtype=torch.float64) # 返回的tensor默认具有相同的torch.dtype和torch.device print(x) x = torch.randn_like(x, dtype=torch.float) # 指定新的数据类型 print(x)
# tensor([[1., 1., 1.], # [1., 1., 1.], # [1., 1., 1.], # [1., 1., 1.], # [1., 1., 1.]], dtype=torch.float64) # tensor([[ 0.6035, 0.8110, -0.0451], # [ 0.8797, 1.0482, -0.0445], # [-0.7229, 2.8663, -0.5655], # [ 0.1604, -0.0254, 1.0739], # [ 2.2628, -0.9175, -0.2251]])
# 通过shape或size()来获取tensor形状 print(x.size()) print(x.shape)
# torch.Size([5, 3]) # torch.Size([5, 3])
运算
# 加法1： y = torch.rand(5, 3) print(x + y)
# 加法2： print(torch.add(x, y))
# 指定输出 result = torch.empty(5, 3) torch.add(x, y, out=result) print(result)
# 加法3：inplace # adds x to y y.add_(x) print(y)
索引
attension：索引出来的结果与原数据共享内存，即修改一个，另一个也被修改了
y = x[0, :] # 矩阵x的第一行 y += 1 print(y) print(x[0, :]) # 原tensor也被修改了
# 改变形状 view() y = x.view(15) z = x.view(-1, 5) print(x.size(), y.size(), z.size())
attension: view()返回的新tensor与原tensor共享内存
# 若不想共享内存，先用clone创造一个副本，再用view x_cp = x.clone().view(15) x -= 1 print(x) print(x_cp)
# item()函数将一个标量tensor转换为一个Python number x = torch.randn(1) print(x) print(x.item())
广播机制
# 两个不同形状tensor可能会引起广播机制 x = torch.arange(1, 3).view(1, 2) print(x) y = torch.arange(1, 4).view(3, 1) print(y) print(x + y)
tensor和NumPy相互转换
numpy()和from_numpy()产生的tensor和NumPy array实际使用的相同的内存
# tensor --> numpy a = torch.ones(5) b = a.numpy() print(a, b) a += 1 print(a, b) b += 1 print(a, b)
# numpy --> tensor import numpy as np a = np.ones(5) b = torch.from_numpy(a) print(a, b) a += 1 print(a, b) b += 1 print(a, b)
# 直接用torch.tensor()将NumPy数组转换成tensor，该方法是将数据拷贝，返回的tensor和原来的数据不再共享内存 # 用torch.tensor()转换时不会共享内存 c = torch.tensor(a) a += 1 print(a, c)
测试是否是GPU版的Pytorch
# 只会在GPU版本运行 if torch.cuda.is_available(): device = torch.device("cuda") # GPU y = torch.ones_like(x, device=device) # 创建一个在GPU上的tensor x = x.to(device) # 等价与x.to("cuda") z = x + y print(z) print(z.to("cpu", torch.double))