![](https://img-blog.csdnimg.cn/20201014180756925.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
pytorch
ncbnwk
这个作者很懒,什么都没留下…
展开
-
pytorch基础学习1
1.从numpy导入 import torch import numpy as np a=np.array([2,2.3]) b=torch.from_numpy(a) print(a) print(b) a=np.ones([2,3]) b=torch.from_numpy(a) print(a) print(b) 结果:[2. 2.3] tensor([2.0000, 2.3000],...原创 2019-07-30 13:00:38 · 72 阅读 · 0 评论 -
pytorch-7交叉商1
定义: def cross_entropy(input, target, weight=None, size_average=None, ignore_index=-100, reduce=None, reduction='mean'): # type: (Tensor, Tensor, Optional[Tensor], Optional[boo...原创 2019-08-01 21:16:28 · 189 阅读 · 0 评论 -
pytorch-6线性优化
1.可视化,meshgrid合并x,y def fun(x): return (x[0]**2+x[1]-11)**2+(x[0]+x[1]**2-7)**2 x=np.arange(-6,6,0.1) y=np.arange(-6,6,0.1) X,Y=np.meshgrid(x,y) print(X.shape) print(Y.shape) Z=fun([X,Y]) fig=p...原创 2019-08-01 20:53:02 · 148 阅读 · 0 评论 -
pytorch5求导
import torch from torch.nn import functional x=torch.ones(1,requires_grad=True) print(x) w=torch.full([1],6,requires_grad=True) mse=functional.mse_loss(x,x*w) print(mse)#(1-6)**2 print(torch.autograd...原创 2019-08-01 00:32:03 · 78 阅读 · 0 评论 -
pytorch基础学习5
1.where import torch cond=torch.tensor([[0.6,0.4],[0.7,0.3]]) a=torch.tensor([[0.,0.],[0.,0.]]) b=torch.tensor([[1.,1.],[1.,1.]]) c=torch.where(cond>0.5,a,b) print(a) print(b) print(c) 结果:tensor...原创 2019-07-31 22:15:26 · 89 阅读 · 0 评论 -
pytourch基础学习4
1.matmul/@/mm(二维)矩阵相乘 import torch a=torch.randn(4,2,3,8) b=torch.randn(4,2,8,8) print(torch.matmul(a,b).shape) 结果:torch.Size([4, 2, 3, 8]) 2.pow/** import torch a=torch.full([2,2],9) print(a) b...原创 2019-07-31 21:21:00 · 279 阅读 · 0 评论 -
pytourch基础学习3
1.合并 import torch a=torch.randn(5,2,3,8) b=torch.randn(4,2,3,8) print(torch.cat([a,b],dim=0).shape) 结果:torch.Size([9, 2, 3, 8]) 2.stack增加维度 import torch a=torch.randn(4,2,3,8) b=torch.randn(4,2,...原创 2019-07-31 20:31:07 · 183 阅读 · 0 评论 -
pytorch基础学习2
1.切片 import torch b=torch.tensor([[[1, 2, 3,4]]]) print(b) a=b[:,:,0:4:2].shape print(a) print(b[:,:,0:4:2]) print(b) 结果:tensor([[[1, 2, 3, 4]]]) torch.Size([1, 1, 2]) tensor([[[1, 3]]]) tensor([[[...原创 2019-07-30 14:22:51 · 70 阅读 · 0 评论