使用pytorch进行图分类

如何解决使用pytorch进行图分类

我正在尝试执行图形分类。我有一个看起来像这样的DGL图列表

DGLGraph(num_nodes=64267,num_edges=155523,ndata_schemes={}
         edata_schemes={'norm': Scheme(shape=(),dtype=torch.float32),'rel_type': Scheme(shape=(17,),dtype=torch.float64)

及其对应的标签为张量（[0，1]）。由于我对PyTorch并不熟悉，因此我在遵循一个示例。 型号定义如下

def gcn_message(edges):
    # The argument is a batch of edges.
    # This computes a (batch of) message called 'msg' using the source node's feature 'h'.
    return {'msg' : edges.src['h']}

def gcn_reduce(nodes):
    # The argument is a batch of nodes.
    # This computes the new 'h' features by summing received 'msg' in each node's mailbox.
    return {'h' : torch.sum(nodes.mailbox['msg'],dim=1)}

# Define the GCNLayer module
class GCNLayer(nn.Module):
    def __init__(self,in_feats,out_feats):
        super(GCNLayer,self).__init__()
        self.linear = nn.Linear(in_feats,out_feats)

    def forward(self,g,inputs):
        # g is the graph and the inputs is the input node features
        # first set the node features
        g.ndata['h'] = inputs
        # trigger message passing on all edges
        g.send(g.edges(),gcn_message)
        # trigger aggregation at all nodes
        g.recv(g.nodes(),gcn_reduce)
        # get the result node features
        h = g.ndata.pop('h')
        # perform linear transformation
        return self.linear(h)

class GCN(nn.Module):
    def __init__(self,hidden_size,num_classes):
        super(GCN,self).__init__()
        self.gcn1 = GCNLayer(in_feats,hidden_size)
        self.gcn2 = GCNLayer(hidden_size,num_classes)

    def forward(self,inputs):
        h = self.gcn1(g,inputs)
        h = torch.relu(h)
        h = self.gcn2(g,h)
        return h
# The first layer transforms input features of size of 41 to a hidden size of 5.
# The second layer transforms the hidden layer and produces output features of
# size 2,corresponding to the two classification groups
net = GCN(7,16,2)

for epoch in range(epochs):
    epoch_loss = 0
    epoch_logits = []
    labs = []
    # Iterate over batches
    for i,(bg,labels) in enumerate(train_loader):
        logits = net(bg,bg.ndata['h'])
        # we save the logits for visualization later
        train_logits.append(logits.detach().numpy())
        epoch_logits.append(logits.detach().numpy()) 
        labs.append(labels.unsqueeze(1).detach().numpy())
        logp = F.softmax(logits,1)
        loss = loss_fn(logp,labels)

在调用loss_fn时，出现错误ValueError：预期输入batch_size（64267）与目标batch_size（64）相匹配。由于某种原因，图形中的每个节点都被视为不同的输入值，并且模型返回一个它的前兆。排序规则定义为

def collate(samples):
    # The input `samples` is a list of pairs
    #  (graph,label).
    graphs,labels = map(list,zip(*samples))
    batched_graph = dgl.batch(graphs,node_attrs='h')
    batched_graph.set_n_initializer(dgl.init.zero_initializer)
    batched_graph.set_e_initializer(dgl.init.zero_initializer)
    return batched_graph,torch.stack(labels)

我在另一个使用dgllife.model.model_zoo.GCNPredictor的模型中使用此整理，它不会产生任何问题。