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
74
75
76
77
78
79
80
|
import os.path as osp
import time
import torch
import torch.nn.functional as F
from sklearn.metrics import f1_score
from torch_geometric.datasets import PPI
from torch_geometric.loader import DataLoader
from torch_geometric.nn import GATConv
path = osp.join(osp.dirname(osp.realpath(__file__)), '..', 'data', 'PPI')
train_dataset = PPI(path, split='train')
val_dataset = PPI(path, split='val')
test_dataset = PPI(path, split='test')
train_loader = DataLoader(train_dataset, batch_size=1, shuffle=True)
val_loader = DataLoader(val_dataset, batch_size=2, shuffle=False)
test_loader = DataLoader(test_dataset, batch_size=2, shuffle=False)
class Net(torch.nn.Module):
def __init__(self):
super().__init__()
self.conv1 = GATConv(train_dataset.num_features, 256, heads=4,
residual=True)
self.conv2 = GATConv(4 * 256, 256, heads=4, residual=True)
self.conv3 = GATConv(4 * 256, train_dataset.num_classes, heads=6,
concat=False, residual=True)
def forward(self, x, edge_index):
x = F.elu(self.conv1(x, edge_index))
x = F.elu(self.conv2(x, edge_index))
x = self.conv3(x, edge_index)
return x
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = Net().to(device)
loss_op = torch.nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.005)
def train():
model.train()
total_loss = 0
for data in train_loader:
data = data.to(device)
optimizer.zero_grad()
loss = loss_op(model(data.x, data.edge_index), data.y)
total_loss += loss.item() * data.num_graphs
loss.backward()
optimizer.step()
return total_loss / len(train_loader.dataset)
@torch.no_grad()
def test(loader):
model.eval()
ys, preds = [], []
for data in loader:
ys.append(data.y)
out = model(data.x.to(device), data.edge_index.to(device))
preds.append((out > 0).float().cpu())
y, pred = torch.cat(ys, dim=0).numpy(), torch.cat(preds, dim=0).numpy()
return f1_score(y, pred, average='micro') if pred.sum() > 0 else 0
times = []
for epoch in range(1, 101):
start = time.time()
loss = train()
val_f1 = test(val_loader)
test_f1 = test(test_loader)
print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}, Val: {val_f1:.4f}, '
f'Test: {test_f1:.4f}')
times.append(time.time() - start)
print(f"Median time per epoch: {torch.tensor(times).median():.4f}s")
|
