Pytorch Geometric官方例程pytorch_geometric/examples/link_pred.py环境安装教程及图数据集制作

最近需要训练图卷积神经网络（Graph Convolution Neural Network, GCNN），在配置GCNN环境上总结了一些经验。

我觉得对于初学者而言，图神经网络的训练会有2个难点：

①环境配置

②数据集制作

一、环境配置

我最初光想到要给GCNN配环境就觉得有些困难，感觉相比于目标检测、分类识别这些任务用规则数据，图神经网络的模型、数据都是图，所以内心觉得会比较难。

我之前更有一个误区，就是觉得不规则结构的图数据不能用CUDA进行并行加速。实际上，图，在电脑里也是以张量这种规则结构数据存在的，完全能用CUDA进行加速计算，训练GCN前配置CUDA完全OK。

以下是我配置的环境，可用CUDA成功运行link_pred.py

几个关键包的版本：

torch                                2.4.1
torch-geometric               2.3.1
torchaudio                       2.4.1
torchvision                       0.14.0
torchviz                            0.0.2

pandas                             1.0.3

numpy                              1.20.0

 CUDA: 11.8

注意要先安装好CUDA，显示了：

 

再安装GPU版本的torch，不然python检测安装的是cpu版本的torch。这时，就得卸载重新安装了

环境配置成功：

print(torch.__version__)
print(torch.cuda.is_available())

如果CUDA环境安装失败，会打印：

2.4.1+cpu
False

其实只安装torch和CUDA还好，如果你的python中有numpy和pandas可能解决版本之间的冲突会耗费不少时间，我就是在numpy和pandas版本上试了很久，最终找到现在的版本是相互兼容的。

CUDA的版本切换可以参考我的另一篇博客：

CUDA版本切换

二、数据集制作

掌握图数据集制作的关键在于掌握slices切片：

for ...data = Data(x=X, edge_index=Edge_index, edge_label_index=Edge_label_index,             edge_label=Edge_label)data_list.append(data)
data_, slices = self.collate(data_list)  # 将不同大小的图数据对齐，填充
torch.save((data_, slices), self.processed_paths[0])

和CNN不同的是，GCN没有样本维度，需要把所有样本拼成一张大图喂给GCN进行训练 

数据集生成代码：

#作者：zhouzhichao
#创建时间：2025/5/30
#内容：生成200个样本的PYG数据集import h5py
import hdf5storage
import numpy as np
import torch
from torch_geometric.data import InMemoryDataset, Data
from torch_geometric.utils import negative_samplingbase_dir = "D:\\无线通信网络认知\\论文1\\experiment\\直推式拓扑推理实验\\拓扑生成\\200样本\\"N = 30
grapg_size = N
train_n = 31
M = 3000class graph_data(InMemoryDataset):def __init__(self, root, signals=None, tp_list = None, transform=None, pre_transform=None):# self.Signals = Signals# self.Tp_list = Tp_listself.signals = signalsself.tp_list = tp_listsuper().__init__(root, transform, pre_transform)# self.data, self.slices = torch.load(self.processed_paths[0])self.data = torch.load(self.processed_paths[0])# 返回process方法所需的保存文件名。你之后保存的数据集名字和列表里的一致@propertydef processed_file_names(self):return ['gcn_data.pt']# 生成数据集所用的方法def process(self):# data_list = []# for k in range(200):# signals = self.Signals[:, :, k]# tp_list = np.array(mat_file[self.Tp_list[0, k]])signals = self.signalstp_list =self.tp_list# tp = Tp[:,:,k]X = torch.tensor(signals, dtype=torch.float)# 所有的边Edge_index = torch.tensor(tp_list, dtype=torch.long)# 所有的边1标签edge_label = np.ones((tp_list.shape[1]))# edge_label = np.zeros((tp_list.shape[1]))Edge_label = torch.tensor(edge_label, dtype=torch.float)neg_edge_index = negative_sampling(edge_index=Edge_index, num_nodes=grapg_size,num_neg_samples=Edge_index.shape[1], method='sparse')# 拼接正负样本索引# c = 0# for i in range(31):#     for i in range(31):#         if torch.equal(Edge_index[:, i], neg_edge_index[:, i]):#             c = c + 1# print("c: ",c)Edge_label_index = Edge_indexperm = torch.randperm(Edge_index.size(1))Edge_index = Edge_index[:, perm]Edge_index = Edge_index[:, :train_n]Edge_label_index = torch.cat([Edge_label_index, neg_edge_index],dim=-1,)# 拼接正负样本Edge_label = torch.cat([Edge_label,Edge_label.new_zeros(neg_edge_index.size(1))], dim=0)# Edge_label = torch.cat([#     Edge_label,#     Edge_label.new_ones(neg_edge_index.size(1))# ], dim=0)data = Data(x=X, edge_index=Edge_index, edge_label_index=Edge_label_index, edge_label=Edge_label)torch.save(data, self.processed_paths[0])# data_list.append(data)# data_, slices = self.collate(data_list)  # 将不同大小的图数据对齐，填充# torch.save((data_, slices), self.processed_paths[0])for snr in [0,20,40]:print("snr: ", snr)mat_file = h5py.File(base_dir + str(N) + '_nodes_dataset_snr-' + str(snr) + '_M_' + str(M) + '.mat', 'r')# mat_file = hdf5storage.loadmat(base_dir + str(N) + '_nodes_dataset_snr-' + str(snr) + '_M_' + str(M) + '.mat', 'r')# 获取数据集Signals = mat_file["Signals"][()]# signals = np.swapaxes(signals, 1, 0)Tp = mat_file["Tp"][()]Tp_list = mat_file["Tp_list"][()]# tp_list = tp_list - 1# 关闭文件# mat_file.close()# graph_data("gcn_data")# n = Signals.shape[2]n = 10for i in range(n):signals = Signals[:,:,i]tp_list = np.array(mat_file[Tp_list[0, i]])root = "gcn_data-"+str(i)+"_N_"+str(N)+"_snr_"+str(snr)+"_train_n_"+str(train_n)+"_M_"+str(M)graph_data(root, signals = signals, tp_list = tp_list)print("")print("...图数据生成完成...")

训练代码：

#作者：zhouzhichao
#创建时间：25年5月29日
#内容：统计图中有关系节点和无关系节点的GCN特征欧式距离import sys
import torch
import random
import numpy as np
import pandas as pd
from torch_geometric.nn import GCNConv
from sklearn.metrics import roc_auc_score
sys.path.append('D:\无线通信网络认知\论文1\experiment\直推式拓扑推理实验\GCN推理')
from gcn_dataset import graph_data
print(torch.__version__)
print(torch.cuda.is_available())mode = "gcn"class Net(torch.nn.Module):def __init__(self):super().__init__()self.conv1 = GCNConv(Input_L, 1000)self.conv2 = GCNConv(1000, 20)def encode(self, x, edge_index):x1 = self.conv1(x, edge_index)x1_1 = x1.relu()x2 = self.conv2(x1_1, edge_index)x2_2 = x2.relu()return x2_2def decode(self, z, edge_label_index):# 节点和边都是矩阵，不同的计算方法致使：节点->节点，节点->边# nodes_relation = (z[edge_label_index[0]] * z[edge_label_index[1]]).sum(dim=-1)# distances  = torch.norm(z[edge_label_index[0]] - z[edge_label_index[1]], dim=-1)distance_squared = torch.sum((z[edge_label_index[0]] - z[edge_label_index[1]]) ** 2, dim=-1)# print("distance_squared: ",distance_squared)return distance_squareddef decode_all(self, z):prob_adj = z @ z.t()  # 得到所有边概率矩阵return (prob_adj > 0).nonzero(as_tuple=False).t()  # 返回概率大于0的边，以edge_index的形式@torch.no_grad()def test(self,input_data):model.eval()z = model.encode(input_data.x, input_data.edge_index)out = model.decode(z, input_data.edge_label_index).view(-1)out = 1 - outN = 30
train_n = 31
M = 3000
# snr = -20
# for train_n in range(1,51):
# for M in range(3000, 499, -100):
for snr in [0,20,40]:print("snr: ", snr)for I in range(10):root = "gcn_data-"+str(I)+"_N_"+str(N)+"_snr_"+str(snr)+"_train_n_"+str(train_n)+"_M_"+str(M)gcn_data = graph_data(root)Input_L = gcn_data.x.shape[1]model = Net()# model = Net().to(device)optimizer = torch.optim.Adam(params=model.parameters(), lr=0.01)criterion = torch.nn.BCEWithLogitsLoss()def train():model.train()optimizer.zero_grad()z = model.encode(gcn_data.x, gcn_data.edge_index)# out = model.decode(z, train_data.edge_label_index).view(-1).sigmoid()out = model.decode(z, gcn_data.edge_label_index).view(-1)out = 1 - outloss = criterion(out, gcn_data.edge_label)loss.backward()optimizer.step()return lossmin_loss = 99999count = 0#早停for epoch in range(10000):loss = train()if loss<min_loss:min_loss = losscount = 0count = count + 1if count>100:breakprint("epoch:  ",epoch,"   loss: ",round(loss.item(),2), "   min_loss: ",round(min_loss.item(),2))z = model.encode(gcn_data.x, gcn_data.edge_index)out = model.decode(z, gcn_data.edge_label_index).view(-1)list_0 = []list_1 = []for i in range(len(gcn_data.edge_label)):true_label = gcn_data.edge_label[i].item()euclidean_distance_value = out[i].item()if true_label==1:list_1.append(euclidean_distance_value)if true_label==0:list_0.append(euclidean_distance_value)minlength = min(len(list_1), len(list_0))list_1 = random.sample(list_1, minlength)list_0 = random.sample(list_0, minlength)value = list_1 + list_0large_class = list(np.full(len(value), snr))small_class = list(np.full(len(list_1), 1)) + list(np.full(len(list_0), 0))data = {'large_class': large_class,'small_class': small_class,'value': value}# 创建一个 DataFramedf = pd.DataFrame(data)## # 保存到 Excel 文件file_path = 'D:\无线通信网络认知\论文1\大修意见\图聚类、阈值相似性图实验补充\\' + mode + '_similarity_' + str(snr) + 'db_'+str(I)+'.xlsx'df.to_excel(file_path, index=False)