pytorch geometric (PYG)入门

客官°小女子只卖身不卖艺 2022-09-12 12:46 489阅读 0赞

在PyG中通过`torch_geometric.data.Data`创建一个简单的图，具有如下属性：

*  `data.x`：节点的特征矩阵，shape： `[num_nodes, num_node_features]`
 *  `data.edge_index`：边的矩阵，shape：`[2, num_edges]`
 *  `data.edge_attr`：边的属性矩阵，shape：`[num_edges, num_edges_features]`
 *  `data.y`：节点的分类任务shape：`[num_nodes, *]`，图分类任务shape:`[1, *]`
 *  `data.pos`：节点的位置矩阵，shape`[num_nodes,num_dimension]`

创建一个简单的图：

import torch
    from torch_geometric.data import Data
    
    # 定义了边的表示，是无向图，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)
    # 有三个节点，第0个节点特征是[-1]，第一个节点特征是[0], 第二个节点特征是[1]
    data = Data(x=x, edge_index=edge_index)

`Data(x=[3, 1], edge_index=[2, 4])`中`x=[3,1]`表示有三个节点，每个节点一个特征，`edge_index=[2, 4]`表示有四条边  
![在这里插入图片描述][c362b73568d64f1fa3f8cd914738a6c1.png]  
![在这里插入图片描述][0cdd5f55ba1c4a10abbaec3225a0fa66.png]  
也可以通过下面的方式创建边：主要是`edge_index.t().contiguous()`

import torch
    from torch_geometric.data import Data
    
    edge_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（节点、边、图的一些属性），`data`还提供了额外的方法：

print(data.keys)
    >>> ['x', 'edge_index']
    # 节点的特征
    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
    
    # 边的属性
    'edge_attr' in data
    >>> False
    # 节点的数量
    data.num_nodes
    >>> 3
    # 边的数量
    data.num_edges
    >>> 4
    # 节点的特征数量
    data.num_node_features
    >>> 1
    
    # 是否拥有孤立的节点
    data.has_isolated_nodes()
    >>> False
    
    # 是否一个环
    data.has_self_loops()
    >>> False
    
    # 是不是有向图
    data.is_directed()
    >>> False
    
    # Transfer data object to GPU.将data转到gpu
    device = torch.device('cuda')
    data = data.to(device)

创建好data之后，PyG内置了一些公开的数据集，可以导入：

from torch_geometric.datasets import TUDataset
    
    # 数据集是对图进行分类的任务
    dataset = TUDataset(root='/tmp/ENZYMES', name='ENZYMES')
    # 有600个图
    len(dataset)
    >>> 600
    # 图的类别数量6
    dataset.num_classes
    >>> 6
    # 图的每个节点的特征数量是3
    dataset.num_node_features
    >>> 3
    # 选择第一个图
    data = dataset[0]
    >>> Data(edge_index=[2, 168], x=[37, 3], y=[1])
    # 无向图
    data.is_undirected()
    >>> True

使用`Cora`数据集：

dataset = Planetoid(root='/tmp/Cora', name='Cora')
    >>> Cora()
    
    len(dataset)
    >>> 1
    
    dataset.num_classes
    >>> 7
    
    dataset.num_node_features
    >>> 1433
    # 获得这张图
    data = dataset[0]
    # train_mask表示训练那些节点（140个），test_mask表示测试哪些节点（1000个）
    >>> Data(edge_index=[2, 10556], test_mask=[2708],
             train_mask=[2708], val_mask=[2708], x=[2708, 1433], y=[2708])
    
    data.is_undirected()
    >>> True
    
    data.train_mask.sum().item()
    >>> 140
    
    data.val_mask.sum().item()
    >>> 500
    
    data.test_mask.sum().item()
    >>> 1000

# PyG实现GCN、GraphSage、GAT #

GCN实现

from torch_geometric.datasets import Planetoid
    
    dataset = 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, GATConv
    
    dataset = 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_index
            x = 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实现：

from torch_geometric.datasets import Planetoid
    import torch
    import torch.nn.functional as F
    from torch_geometric.nn import GCNConv, SAGEConv, GATConv
    
    dataset = 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_index
            x = 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 实现：

from torch_geometric.datasets import Planetoid
    import torch
    import torch.nn.functional as F
    from torch_geometric.nn import GCNConv, SAGEConv, GATConv
    
    dataset = 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_index
            x = 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]))

[c362b73568d64f1fa3f8cd914738a6c1.png]: /images/20220828/458ae6c992e546af8e130f99ac9f16d0.png
[0cdd5f55ba1c4a10abbaec3225a0fa66.png]: /images/20220828/984ba799ef21408586c794bc1706beea.png