just_so_so_fnc的博客

import torch import torch.nn as nn import torch.nn.functional as F import numpy as np import matplotlib.pyplot as plt """ 引用上一篇博客中所用到的数据处理函数 """ from coraDatasetsProcess import main node_nums,feature_dims,label_list,feat_Matrix,degree_list,cites,X_Node,..

import os import numpy as np from tqdm import tqdm import matplotlib.pyplot as plt import torch import torch.nn as nn import torch.nn.functional as F ''' node_num, feat_dim, stat_dim, num_class, T feat_Matrix, X_Node, X_Neis, dg_list cora.content共有2708.

#导入模块 import torch import torchvision#数据集库 import torchvision.transforms as transforms #数据集加载模块 transform=transforms.Compose( [transforms.ToTensor(), transforms.Normalize((0.5,0.5,0.5),(0.5,...

import torch.nn as nn import torch import torch.nn.functional as F #定义网络模块 主要包括初始化、前向传播、数据维度处理 class Net(nn.Module): #初始化 def __init__(self,channel,kernel_count,kenel_size): super(N...

import torch import torchvision#包含一些数据集，像如mnist import torch.utils.data as Data import torch.nn as nn import matplotlib.pyplot as plt #超参数 EPOCH=1 BATCH_SIZE=50 LR=0.01 DOWNLOAD_MNIST=True#是否下载数据集 ...

import torch import torch.utils.data as Data import torch.nn.functional as f import matplotlib.pyplot as plt #指定超参数 LR=0.01#学习率 BATCH_SIZE=32#批数据的大小 EPOCH=12#迭代次数 #构造数据集 x=torch.unsqueeze(torch.lin...

import torch import torch.utils.data as Data#导入pytorch的数据处理模块 #DataLoader是一种处理数据的工具，能够自动处理tensor形式的数据，训练过程中能更好的迭代数据 BATCH_SIZE=8#批训练的数据个数 #原始数据 x=torch.linspace(1,10,10) y=torch.linspace(10,1,10) ...

import torch import torch.nn.functional as f #构造假数据 # x=torch.squeeze(torch.linspace(-1,1,100))#shape为[100]的数组 x=torch.unsqueeze(torch.linspace(0-1,1,100),dim=1)#shape为(100,1)的tensor y=x.pow(2)+0.2*...

import torch import torch.nn.functional as f #定义一个calss类继承pytouch class Net(torch.nn.Module): #初始化函数 def __init__(self,n_feature,n_hidden,n_output): super(Net,self).__init__() ...

#该案例主要是做简单节点分类任务的模型训练 import torch import matplotlib.pyplot as plt #数据集构造 都是tensor张良结构 n_data=torch.ones(100,2)#数据基本形态 100x2的维度 x0=torch.normal(2*n_data,1)#第一种类型的数据,服从为1的正态分布 100x2的维度 横坐标和纵坐标 y0=t...

import torch import matplotlib.pyplot as plt #torch.unsqueeze()度扩充，将1*100的tensor变为100*1的维度，作为完整数据集一次性喂给网络 还有squeeze正好相反 x=torch.unsqueeze(torch.linspace(-1,1,100),dim=1)#训练集-1到1共100个数据 y=x.pow(2)+...