权重与求和
- class dgl.nn.pytorch.glob.WeightAndSum(in_feats)[source]
Bases:
Module计算原子的重要性权重并执行加权求和。
- Parameters:
in_feats (int) – 输入原子特征大小
示例
以下示例使用PyTorch后端。
>>> import dgl >>> import torch as th >>> from dgl.nn import WeightAndSum >>> >>> g1 = dgl.rand_graph(3, 4) # g1 is a random graph with 3 nodes and 4 edges >>> g1_node_feats = th.rand(3, 5) # feature size is 5 >>> g1_node_feats tensor([[0.8948, 0.0699, 0.9137, 0.7567, 0.3637], [0.8137, 0.8938, 0.8377, 0.4249, 0.6118], [0.5197, 0.9030, 0.6825, 0.5725, 0.4755]]) >>> >>> g2 = dgl.rand_graph(4, 6) # g2 is a random graph with 4 nodes and 6 edges >>> g2_node_feats = th.rand(4, 5) # feature size is 5 >>> g2_node_feats tensor([[0.2053, 0.2426, 0.4111, 0.9028, 0.5658], [0.5278, 0.6365, 0.9990, 0.2351, 0.8945], [0.3134, 0.0580, 0.4349, 0.7949, 0.3891], [0.0142, 0.2709, 0.3330, 0.8521, 0.6925]]) >>> >>> weight_and_sum = WeightAndSum(5) # create a weight and sum layer(in_feats=16)
案例1：输入单个图形
>>> weight_and_sum(g1, g1_node_feats) tensor([[1.2194, 0.9490, 1.3235, 0.9609, 0.7710]], grad_fn=<SegmentReduceBackward>)
案例2：输入一批图形
构建一批DGL图并将所有图的节点特征连接成一个张量。
>>> batch_g = dgl.batch([g1, g2]) >>> batch_f = th.cat([g1_node_feats, g2_node_feats]) >>> >>> weight_and_sum(batch_g, batch_f) tensor([[1.2194, 0.9490, 1.3235, 0.9609, 0.7710], [0.5322, 0.5840, 1.0729, 1.3665, 1.2360]], grad_fn=<SegmentReduceBackward>)
注释
WeightAndSum模块通常用于分子属性预测网络中， 参见dgl-lifesci中的GCN预测器 以了解如何使用WeightAndSum层获取图读出输出。