人工智能

import torch import numpy as np a = torch.tensor([[[1]]]) #只有一个数据的时候，获取其数值 print(a.item()) #tensor转化为nparray b = a.numpy() print(b,type(b),type(a)) #获取张量的形状 a = torch.tensor(np.ara…

import torch import numpy as np print(torch.tensor([1,2,3])) print(torch.tensor(np.arange(15).reshape(3,5))) print(torch.empty([3,4])) print(torch.ones([3,4])) print(torch.zeros([3…

import torch import numpy as np device = torch.device(“cuda:0” if torch.cuda.is_available() else “cpu”) x = torch.tensor(np.arange(15).reshape(3,5)) if torch.cuda.is_available(): d…

  示例： import torch import torch.nn as nn from torch import optim class MyModel(nn.Module): def __init__(self): super(MyModel,self).__init__() self.lr = nn.Linear(1,1) def forward(s…

在pytorch当中，有两种方式可以实现交叉熵，而我们把softmax概率传入传入对数似然损失得到的损失函数叫做“交叉熵损失” 在pytorch当中有两种方法实现交叉熵损失： 实现方式1： criterion=nn.CrossEntropyLoss() loss=criterion(input,target) 实现方式2: #对输出值进行计算softmax，…

import torch import torch.utils.data as Data torch.manual_seed(1) # reproducible # BATCH_SIZE = 5 BATCH_SIZE = 8 # 每次使用8个数据同时传入网路 x = torch.linspace(1, 10, 10) # this is x data (to…

import torch import numpy as np http://pytorch.org/docs/torch.html#math-operations convert numpy to tensor or vise versa # convert numpy to tensor or vise versa np_data = np.arange…

import torch import torch.nn.functional as F # replace following class code with an easy sequential network class Net(torch.nn.Module): def __init__(self, n_feature, n_hidden, n_ou…