MaxPooling
- class dgl.nn.pytorch.glob.MaxPooling[源码]
基类:
Module在图的节点上应用最大池化。
\[r^{(i)} = \max_{k=1}^{N_i}\left( x^{(i)}_k \right)\]注意
输入：可以是一个图，也可以是一批图。如果使用一批图，请确保所有图中的节点具有相同的特征大小，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 MaxPooling >>> >>> 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]]) >>> >>> maxpool = MaxPooling() # create a max pooling layer
情况1：输入单个图
>>> maxpool(g1, g1_node_feats) tensor([[0.8948, 0.9030, 0.9137, 0.7567, 0.6118]])
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]) >>> >>> maxpool(batch_g, batch_f) tensor([[0.8948, 0.9030, 0.9137, 0.7567, 0.6118], [0.5278, 0.6365, 0.9990, 0.9028, 0.8945]])