import torch
#經(jīng)典方式
device = torch.device("cuda:0")
x = torch.tensor([1,2],dtype = torch.float32,device = device,requires_grad=True)
w = sum(2 * x)
w.backward()
print(x.device)
print(x.dtype)
print(x.grad)
#Tensor
y = torch.Tensor([1,2,3])
#等價(jià)于
y = torch.FloatTensor([1,2,3])#32位浮點(diǎn)型
#后者聲明打開梯度
y.requires_grad = True
#還有其他類型,常用的
torch.LongTensor(2,3)
torch.shortTensor(2,3)
torch.IntTensor(2,3)
w = sum(2 * y)
w.backward()
print(y.grad)
print(y.dtype)

x = torch.linspace(1,10,10,dtype = torch.float32,requires_grad = True)
y = torch.ones(10)
z = torch.zeros((2,4))
w = torch.randn((2,3))#從標(biāo)準(zhǔn)正態(tài)分布（均值為0，方差為1）上隨機(jī)采用，高斯噪聲點(diǎn)，而rand相當(dāng)于在0，1間隨機(jī)采樣
#torch.normal()????
print(x)
print(y)
print(z)
print(w)

np_data = np.arange(2,13,2).reshape((2,3))
torch_data = torch.from_numpy(np_data)#numpy轉(zhuǎn)tensor
print('\nnumpy',np_data)
print('\ntorch',torch_data)

import torch
x = torch.arange(0,10,1).reshape(2,-1)#size=(2,5)
y = torch.ones(10).reshape(2,-1)#size=(2,5)
print(x)
print(y)
w = torch.cat((x,y),dim = 0)#默認(rèn)從size最左邊開始，這里結(jié)果為：（2+2，5）
z = torch.cat((x,y),dim = 1)#（2，5+5）
print(w,w.size())
print(z,z.size())
#還有種stack()

x = torch.rand((2,2),dtype = torch.float32)
print(x.dtype)
x = x.double()
print(x.dtype)
x = x.int()
print(x)

x = torch.LongTensor((2,2))
print(x.dtype)
x = x.type(torch.float32)
print(x.dtype)

x = torch.arange(0,4,1).reshape(2,-1)
print(x)
print(x * x )#直接相乘
print(torch.mm(x,x))#矩陣乘法
print(x + 1)#廣播
print(x.numpy())#轉(zhuǎn)換成numpy

 torch.squeeze(input)#去掉維度為1的維數(shù)
 torch.unsqueeze(input,dim)#指定位置增加一維