Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
You can not select more than 25 topics
Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
闫广庆
42693eb835
|
1 year ago | |
|---|---|---|
| .. | ||
| __init__.py | 1 year ago | |
| graph_sage_show.py | 1 year ago | |
| readme.md | 1 year ago | |
readme.md
graphsage是一个可以融合本身向量特征及网络特征的一种算法。
通过对graph sage构建数据集过程观察的观察我们可以发现模型的输入有两个特征
from torch_geometric.nn import GraphSAGE
import torch
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = GraphSAGE(data.num_node_features, hidden_channels=64,
num_layers=2).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
# batch x 是一个 [批量节点数量，节点特征向量] batch edge_indexs是一个节点-节点之间的关系列表
h = model(batch.x, batch.edge_index)
No Description
Python Markdown
