1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
|
import os.path as osp
import time
import torch
import torch.nn.functional as F
import torch_geometric.transforms as T
from torch_geometric.datasets import Planetoid
from torch_geometric.nn import SuperGATConv
dataset = 'Cora'
path = osp.join(osp.dirname(osp.realpath(__file__)), '..', 'data', dataset)
dataset = Planetoid(path, dataset, transform=T.NormalizeFeatures())
data = dataset[0]
class Net(torch.nn.Module):
def __init__(self):
super().__init__()
self.conv1 = SuperGATConv(dataset.num_features, 8, heads=8,
dropout=0.6, attention_type='MX',
edge_sample_ratio=0.8, is_undirected=True)
self.conv2 = SuperGATConv(8 * 8, dataset.num_classes, heads=8,
concat=False, dropout=0.6,
attention_type='MX', edge_sample_ratio=0.8,
is_undirected=True)
def forward(self, x, edge_index):
x = F.dropout(x, p=0.6, training=self.training)
x = F.elu(self.conv1(x, edge_index))
att_loss = self.conv1.get_attention_loss()
x = F.dropout(x, p=0.6, training=self.training)
x = self.conv2(x, data.edge_index)
att_loss += self.conv2.get_attention_loss()
return F.log_softmax(x, dim=-1), att_loss
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model, data = Net().to(device), data.to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.005, weight_decay=5e-4)
def train(data):
model.train()
optimizer.zero_grad()
out, att_loss = model(data.x, data.edge_index)
loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask])
loss += 4.0 * att_loss
loss.backward()
optimizer.step()
@torch.no_grad()
def test(data):
model.eval()
out, accs = model(data.x, data.edge_index)[0], []
for _, mask in data('train_mask', 'val_mask', 'test_mask'):
pred = out[mask].argmax(1)
acc = pred.eq(data.y[mask]).sum().item() / mask.sum().item()
accs.append(acc)
return accs
times = []
for epoch in range(1, 501):
start = time.time()
train(data)
train_acc, val_acc, test_acc = test(data)
print(f'Epoch: {epoch:03d}, Train: {train_acc:.4f}, Val: {val_acc:.4f}, '
f'Test: {test_acc:.4f}')
times.append(time.time() - start)
print(f"Median time per epoch: {torch.tensor(times).median():.4f}s")
|
