AvgPooling
- class dgl.nn.pytorch.glob.AvgPooling[source]
基类:
Module对图中的节点应用平均池化。
\[r^{(i)} = \frac{1}{N_i}\sum_{k=1}^{N_i} x^{(i)}_k\]备注
输入：可以是单个图，或一批图。如果使用一批图，请确保所有图中的节点具有相同的特征尺寸，并将节点的特征连接起来作为输入。
示例
以下示例使用 PyTorch 后端。
>>> import dgl >>> import torch as th >>> from dgl.nn import AvgPooling >>> >>> 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]]) >>> >>> avgpool = AvgPooling() # create an average pooling layer
情况 1：输入单个图
>>> avgpool(g1, g1_node_feats) tensor([[0.7427, 0.6222, 0.8113, 0.5847, 0.4837]])
情况 2：输入一批图
构建一批 DGL 图，并将所有图的节点特征连接到一个张量中。
>>> batch_g = dgl.batch([g1, g2]) >>> batch_f = th.cat([g1_node_feats, g2_node_feats]) >>> >>> avgpool(batch_g, batch_f) tensor([[0.7427, 0.6222, 0.8113, 0.5847, 0.4837], [0.2652, 0.3020, 0.5445, 0.6962, 0.6355]])