)
LZ之前一直使用的都是tensorflow对pytorch这个深度框架一直有所耳闻只是看过部分代码自己却没怎么写过感觉还是要学习下不然跟不上年轻人的时代呢主要都是pytorch的tutorial的example自己运行下然后在稍微注释下内容比较简单Pytorch高阶玩家可忽略。#载入对应包from__future__importprint_functionimporttorch#看下版本呗print(torch.__version__)1.1.0#当使用的matrix为空时初始值相当随意。。。xtorch.empty(5,3)print(x)tensor([[ 0.0000e00, 0.0000e00, 0.0000e00], [ 0.0000e00, 0.0000e00, 0.0000e00], [ 0.0000e00, 0.0000e00, 0.0000e00], [ 0.0000e00, 9.1084e-44, 0.0000e00], [-1.5327e33, 3.0915e-41, 2.5906e-15]])#随机初始化个矩阵这个和tf差不多xtorch.rand(5,3)print(x)tensor([[0.9989, 0.1704, 0.8226], [0.0776, 0.9894, 0.5031], [0.3808, 0.3658, 0.4930], [0.0226, 0.0428, 0.9701], [0.2032, 0.0144, 0.8480]])#初始化为0typelongxtorch.zeros(5,3,dtypetorch.long)print(x)tensor([[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]])#创建个tensorxtorch.tensor([5.5,3])print(x)tensor([5.5000, 3.0000])#对于已有tensor重新赋值使用xx.new_ones(5,3,dtypetorch.double)print(x)xtorch.randn_like(x,dtypetorch.float)print(x)tensor([[1., 1., 1.], [1., 1., 1.], [1., 1., 1.], [1., 1., 1.], [1., 1., 1.]], dtypetorch.float64) tensor([[-1.2955, -0.5346, -0.3851], [ 0.0423, 0.7751, -0.8816], [-1.0434, -0.6452, 1.6098], [-0.7102, -1.1221, -0.5180], [-0.0641, 0.0103, 0.2643]])#输出尺寸print(x.size())torch.Size([5, 3])#开始两个变量了加减乘除。。。ytorch.rand(5,3)print(x,y)tensor([[-1.2955, -0.5346, -0.3851], [ 0.0423, 0.7751, -0.8816], [-1.0434, -0.6452, 1.6098], [-0.7102, -1.1221, -0.5180], [-0.0641, 0.0103, 0.2643]]) tensor([[0.0126, 0.4379, 0.6608], [0.6111, 0.3980, 0.6987], [0.5446, 0.8241, 0.3343], [0.0104, 0.6765, 0.3375], [0.5786, 0.2635, 0.2601]])y.add_(x)print(y)tensor([[-1.2829, -0.0967, 0.2757], [ 0.6534, 1.1731, -0.1829], [-0.4988, 0.1789, 1.9440], [-0.6999, -0.4456, -0.1805], [ 0.5145, 0.2738, 0.5244]])print(x[:,1])tensor([-0.5346, 0.7751, -0.6452, -1.1221, 0.0103])#resize的操作啦xtorch.randn(4,4)yx.view(16)zx.view(-1,8)print(x.size(),y.size(),z.size())torch.Size([4, 4]) torch.Size([16]) torch.Size([2, 8])#输出对应tensor值tf要session run才行xtorch.randn(1)print(x)print(x.item())tensor([-1.0967]) -1.0967001914978027atorch.ones(5)print(a)tensor([1., 1., 1., 1., 1.])ba.numpy()print(b)[1. 1. 1. 1. 1.]a.add_(1)print(a)print(b)tensor([2., 2., 2., 2., 2.]) [2. 2. 2. 2. 2.]importnumpyasnp anp.ones(5)btorch.from_numpy(a)np.add(a,1,outa)print(a)print(b)[2. 2. 2. 2. 2.] tensor([2., 2., 2., 2., 2.], dtypetorch.float64)#移动数据GPU或者CPUiftorch.cuda.is_available():devicetorch.device(cuda)ytorch.ones_like(x,devicedevice)xx.to(device)zxyprint(z)print(z.to(cpu,torch.double))tensor([-0.0967], devicecuda:0) tensor([-0.0967], dtypetorch.float64)好像基本操作还不是很难后续继续学习中。。。参考地址https://pytorch.org/tutorials/beginner/blitz/tensor_tutorial.html#sphx-glr-beginner-blitz-tensor-tutorial-py
LZ之前一直使用的都是tensorflow对pytorch这个深度框架一直有所耳闻只是看过部分代码自己却没怎么写过感觉还是要学习下不然跟不上年轻人的时代呢主要都是pytorch的tutorial的example自己运行下然后在稍微注释下内容比较简单Pytorch高阶玩家可忽略。#载入对应包from__future__importprint_functionimporttorch#看下版本呗print(torch.__version__)1.1.0#当使用的matrix为空时初始值相当随意。。。xtorch.empty(5,3)print(x)tensor([[ 0.0000e00, 0.0000e00, 0.0000e00], [ 0.0000e00, 0.0000e00, 0.0000e00], [ 0.0000e00, 0.0000e00, 0.0000e00], [ 0.0000e00, 9.1084e-44, 0.0000e00], [-1.5327e33, 3.0915e-41, 2.5906e-15]])#随机初始化个矩阵这个和tf差不多xtorch.rand(5,3)print(x)tensor([[0.9989, 0.1704, 0.8226], [0.0776, 0.9894, 0.5031], [0.3808, 0.3658, 0.4930], [0.0226, 0.0428, 0.9701], [0.2032, 0.0144, 0.8480]])#初始化为0typelongxtorch.zeros(5,3,dtypetorch.long)print(x)tensor([[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]])#创建个tensorxtorch.tensor([5.5,3])print(x)tensor([5.5000, 3.0000])#对于已有tensor重新赋值使用xx.new_ones(5,3,dtypetorch.double)print(x)xtorch.randn_like(x,dtypetorch.float)print(x)tensor([[1., 1., 1.], [1., 1., 1.], [1., 1., 1.], [1., 1., 1.], [1., 1., 1.]], dtypetorch.float64) tensor([[-1.2955, -0.5346, -0.3851], [ 0.0423, 0.7751, -0.8816], [-1.0434, -0.6452, 1.6098], [-0.7102, -1.1221, -0.5180], [-0.0641, 0.0103, 0.2643]])#输出尺寸print(x.size())torch.Size([5, 3])#开始两个变量了加减乘除。。。ytorch.rand(5,3)print(x,y)tensor([[-1.2955, -0.5346, -0.3851], [ 0.0423, 0.7751, -0.8816], [-1.0434, -0.6452, 1.6098], [-0.7102, -1.1221, -0.5180], [-0.0641, 0.0103, 0.2643]]) tensor([[0.0126, 0.4379, 0.6608], [0.6111, 0.3980, 0.6987], [0.5446, 0.8241, 0.3343], [0.0104, 0.6765, 0.3375], [0.5786, 0.2635, 0.2601]])y.add_(x)print(y)tensor([[-1.2829, -0.0967, 0.2757], [ 0.6534, 1.1731, -0.1829], [-0.4988, 0.1789, 1.9440], [-0.6999, -0.4456, -0.1805], [ 0.5145, 0.2738, 0.5244]])print(x[:,1])tensor([-0.5346, 0.7751, -0.6452, -1.1221, 0.0103])#resize的操作啦xtorch.randn(4,4)yx.view(16)zx.view(-1,8)print(x.size(),y.size(),z.size())torch.Size([4, 4]) torch.Size([16]) torch.Size([2, 8])#输出对应tensor值tf要session run才行xtorch.randn(1)print(x)print(x.item())tensor([-1.0967]) -1.0967001914978027atorch.ones(5)print(a)tensor([1., 1., 1., 1., 1.])ba.numpy()print(b)[1. 1. 1. 1. 1.]a.add_(1)print(a)print(b)tensor([2., 2., 2., 2., 2.]) [2. 2. 2. 2. 2.]importnumpyasnp anp.ones(5)btorch.from_numpy(a)np.add(a,1,outa)print(a)print(b)[2. 2. 2. 2. 2.] tensor([2., 2., 2., 2., 2.], dtypetorch.float64)#移动数据GPU或者CPUiftorch.cuda.is_available():devicetorch.device(cuda)ytorch.ones_like(x,devicedevice)xx.to(device)zxyprint(z)print(z.to(cpu,torch.double))tensor([-0.0967], devicecuda:0) tensor([-0.0967], dtypetorch.float64)好像基本操作还不是很难后续继续学习中。。。参考地址https://pytorch.org/tutorials/beginner/blitz/tensor_tutorial.html#sphx-glr-beginner-blitz-tensor-tutorial-py
)
平方复杂度无法被常规优化消除｜TaoToken 统一 Key 通道实测)
