在PyG中通過torch_geometric.data.Data創建一個簡單的圖，具有如下屬性：

• data.x：節點的特征矩陣，shape： [num_nodes, num_node_features]
• data.edge_index：邊的矩陣，shape：[2, num_edges]
• data.edge_attr：邊的屬性矩陣，shape：[num_edges, num_edges_features]
• data.y：節點的分類任務，樣本標簽，shape：[num_nodes, *]，圖分類任務shape:[1, *]
• data.pos：節點的坐標，shape[num_nodes,num_dimension]

創建一個圖

import torch from torch_geometric.data import Data# 定義了邊的表示，是無向圖，所以shape:[2, 4] ,(0,1)(1,0)(1,2)(2,1) edge_index = torch.tensor([[0, 1, 1, 2],[1, 0, 2, 1]], dtype=torch.long)x = torch.tensor([[-1], [0], [1]], dtype=torch.float) # 有三個節點，第0個節點特征是[-1]，第一個節點特征是[0], 第二個節點特征是[1] data = Data(x=x, edge_index=edge_index)

Data(x=[3, 1], edge_index=[2, 4])中x=[3,1]表示有三個節點，每個節點一個特征，edge_index=[2, 4]表示有四條邊


也可以通過下面的方式創建邊：主要是edge_index.t().contiguous()

import torch from torch_geometric.data import Dataedge_index = torch.tensor([[0, 1],[1, 0],[1, 2],[2, 1]], dtype=torch.long) x = torch.tensor([[-1], [0], [1]], dtype=torch.float)data = Data(x=x, edge_index=edge_index.t().contiguous()) >>> Data(edge_index=[2, 4], x=[3, 1])

除了上述的功能（節點、邊、圖的一些屬性），data還提供了額外的方法：

print(data.keys) >>> ['x', 'edge_index'] # 節點的特征 print(data['x']) >>> tensor([[-1.0],[0.0],[1.0]])for key, item in data:print("{} found in data".format(key)) >>> x found in data >>> edge_index found in data# 邊的屬性 'edge_attr' in data >>> False # 節點的數量 data.num_nodes >>> 3 # 邊的數量 data.num_edges >>> 4 # 節點的特征數量 data.num_node_features >>> 1# 是否擁有孤立的節點 data.has_isolated_nodes() >>> False# 是否一個環 data.has_self_loops() >>> False# 是不是有向圖 data.is_directed() >>> False# Transfer data object to GPU.將data轉到gpu device = torch.device('cuda') data = data.to(device)

創建好data之后，PyG內置了一些公開的數據集，可以導入：

from torch_geometric.datasets import TUDataset# 數據集是對圖進行分類的任務 dataset = TUDataset(root='/tmp/ENZYMES', name='ENZYMES') # 有600個圖 len(dataset) >>> 600 # 圖的類別數量6 dataset.num_classes >>> 6 # 圖的每個節點的特征數量是3 dataset.num_node_features >>> 3 # 選擇第一個圖 data = dataset[0] >>> Data(edge_index=[2, 168], x=[37, 3], y=[1]) # 無向圖 data.is_undirected() >>> True

使用Cora數據集：

dataset = Planetoid(root='/tmp/Cora', name='Cora') >>> Cora()len(dataset) >>> 1dataset.num_classes >>> 7dataset.num_node_features >>> 1433 # 獲得這張圖 data = dataset[0] # train_mask表示訓練那些節點（140個），test_mask表示測試哪些節點（1000個） >>> Data(edge_index=[2, 10556], test_mask=[2708],train_mask=[2708], val_mask=[2708], x=[2708, 1433], y=[2708])data.is_undirected() >>> Truedata.train_mask.sum().item() >>> 140data.val_mask.sum().item() >>> 500data.test_mask.sum().item() >>> 1000

PyG實現GCN、GraphSage、GAT

GCN實現

from torch_geometric.datasets import Planetoiddataset = Planetoid(root='/tmp/Cora', name='Cora')from torch_geometric.datasets import Planetoid import torch import torch.nn.functional as F from torch_geometric.nn import GCNConv, SAGEConv, GATConvdataset = Planetoid(root='/tmp/Cora', name='Cora')class GCN_Net(torch.nn.Module):def __init__(self, feature, hidden, classes):super(GCN_Net, self).__init__()self.conv1 = GCNConv(feature, hidden)self.conv2 = GCNConv(hidden, classes)def forward(self, data):x, edge_index = data.x, data.edge_indexx = self.conv1(x, edge_index)x = F.relu(x)x = F.dropout(x, training=self.training)x = self.conv2(x, edge_index)return F.log_softmax(x, dim=1)device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = GCN_Net(dataset.num_node_features, 16, dataset.num_classes).to(device) data = dataset[0] # optimizer = torch.optim.Adam(model.parameters(), lr=0.01) # optimizer = torch.optim.Adam([ # dict(params=model.conv1.parameters(), weight_decay=5e-4), # dict(params=model.conv2.parameters(), weight_decay=0) # ], lr=0.01) optimizer = torch.optim.Adam(model.parameters(),lr=0.01, weight_decay=5e-4)model.train() for epoch in range(1000):optimizer.zero_grad()out = model(data)loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask])correct = out[data.train_mask].max(dim=1)[1].eq(data.y[data.train_mask]).double().sum()# print('epoch:', epoch, ' acc:', correct / int(data.train_mask.sum()))loss.backward()optimizer.step()if epoch % 10 == 9:model.eval()logits, accs = model(data), []for _, mask in data('train_mask', 'val_mask', 'test_mask'):pred = logits[mask].max(1)[1]acc = pred.eq(data.y[mask]).sum().item() / mask.sum().item()accs.append(acc)log = 'Epoch: {:03d}, Train: {:.5f}, Val: {:.5f}, Test: {:.5f}'print(log.format(epoch + 1, accs[0], accs[1], accs[2]))# model.eval() # _, pred = model(data).max(dim=1) # correct = pred[data.test_mask].eq(data.y[data.test_mask]).sum() # acc = int(correct) / int(data.test_mask.sum()) # print(acc)

GraphSage實現：

from torch_geometric.datasets import Planetoid import torch import torch.nn.functional as F from torch_geometric.nn import GCNConv, SAGEConv, GATConvdataset = Planetoid(root='/tmp/Cora', name='Cora')class GraphSage_Net(torch.nn.Module):def __init__(self, features, hidden, classes):super(GraphSage_Net, self).__init__()self.sage1 = SAGEConv(features, hidden)self.sage2 = SAGEConv(hidden, classes)def forward(self, data):x, edge_index = data.x, data.edge_indexx = self.sage1(x, edge_index)x = F.relu(x)x = F.dropout(x, training=self.training)x = self.sage2(x, edge_index)return F.log_softmax(x, dim=1)device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = GraphSage_Net(dataset.num_node_features, 16, dataset.num_classes).to(device) data = dataset[0] # optimizer = torch.optim.Adam(model.parameters(), lr=0.01) # optimizer = torch.optim.Adam([ # dict(params=model.conv1.parameters(), weight_decay=5e-4), # dict(params=model.conv2.parameters(), weight_decay=0) # ], lr=0.01) optimizer = torch.optim.Adam(model.parameters(),lr=0.01, weight_decay=5e-4)model.train() for epoch in range(1000):optimizer.zero_grad()out = model(data)loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask])correct = out[data.train_mask].max(dim=1)[1].eq(data.y[data.train_mask]).double().sum()# print('epoch:', epoch, ' acc:', correct / int(data.train_mask.sum()))loss.backward()optimizer.step()if epoch % 10 == 9:model.eval()logits, accs = model(data), []for _, mask in data('train_mask', 'val_mask', 'test_mask'):pred = logits[mask].max(1)[1]acc = pred.eq(data.y[mask]).sum().item() / mask.sum().item()accs.append(acc)log = 'Epoch: {:03d}, Train: {:.5f}, Val: {:.5f}, Test: {:.5f}'print(log.format(epoch + 1, accs[0], accs[1], accs[2]))

GAT 實現：

from torch_geometric.datasets import Planetoid import torch import torch.nn.functional as F from torch_geometric.nn import GCNConv, SAGEConv, GATConvdataset = Planetoid(root='/tmp/Cora', name='Cora')class GAT_Net(torch.nn.Module):def __init__(self, features, hidden, classes, heads=1):super(GAT_Net, self).__init__()self.gat1 = GATConv(features, hidden, heads=heads)self.gat2 = GATConv(hidden * heads, classes)def forward(self, data):x, edge_index = data.x, data.edge_indexx = self.gat1(x, edge_index)x = F.relu(x)x = F.dropout(x, training=self.training)x = self.gat2(x, edge_index)return F.log_softmax(x, dim=1)device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = GAT_Net(dataset.num_node_features, 16, dataset.num_classes, heads=4).to(device) data = dataset[0] # optimizer = torch.optim.Adam(model.parameters(), lr=0.01) # optimizer = torch.optim.Adam([ # dict(params=model.conv1.parameters(), weight_decay=5e-4), # dict(params=model.conv2.parameters(), weight_decay=0) # ], lr=0.01) optimizer = torch.optim.Adam(model.parameters(),lr=0.01, weight_decay=5e-4)model.train() for epoch in range(1000):optimizer.zero_grad()out = model(data)loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask])correct = out[data.train_mask].max(dim=1)[1].eq(data.y[data.train_mask]).double().sum()# print('epoch:', epoch, ' acc:', correct / int(data.train_mask.sum()))loss.backward()optimizer.step()if epoch % 10 == 9:model.eval()logits, accs = model(data), []for _, mask in data('train_mask', 'val_mask', 'test_mask'):pred = logits[mask].max(1)[1]acc = pred.eq(data.y[mask]).sum().item() / mask.sum().item()accs.append(acc)log = 'Epoch: {:03d}, Train: {:.5f}, Val: {:.5f}, Test: {:.5f}'print(log.format(epoch + 1, accs[0], accs[1], accs[2]))

總結

以上是生活随笔為你收集整理的PYG教程【一】入门的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。