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
81
82
83
84
85
86
87
88
89
90
91
92
93
|
import os.path as osp
import time
import torch
import torch.nn.functional as F
from sklearn.metrics import f1_score
from torch_geometric.data import Batch
from torch_geometric.datasets import PPI
from torch_geometric.loader import ClusterData, ClusterLoader, DataLoader
from torch_geometric.nn import BatchNorm, SAGEConv
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_data = Batch.from_data_list(train_dataset)
cluster_data = ClusterData(train_data, num_parts=50, recursive=False,
save_dir=train_dataset.processed_dir)
train_loader = ClusterLoader(cluster_data, batch_size=1, shuffle=True,
num_workers=12)
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, in_channels, hidden_channels, out_channels, num_layers):
super().__init__()
self.convs = torch.nn.ModuleList()
self.batch_norms = torch.nn.ModuleList()
self.convs.append(SAGEConv(in_channels, hidden_channels))
self.batch_norms.append(BatchNorm(hidden_channels))
for _ in range(num_layers - 2):
self.convs.append(SAGEConv(hidden_channels, hidden_channels))
self.batch_norms.append(BatchNorm(hidden_channels))
self.convs.append(SAGEConv(hidden_channels, out_channels))
def forward(self, x, edge_index):
for conv, batch_norm in zip(self.convs[:-1], self.batch_norms):
x = conv(x, edge_index)
x = batch_norm(x)
x = F.relu(x)
x = F.dropout(x, p=0.2, training=self.training)
return self.convs[-1](x, edge_index)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = Net(in_channels=train_dataset.num_features, hidden_channels=1024,
out_channels=train_dataset.num_classes, num_layers=6).to(device)
loss_op = torch.nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
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)
loss.backward()
optimizer.step()
total_loss += loss.item() * data.num_nodes
return total_loss / train_data.num_nodes
@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, 201):
start = time.time()
loss = train()
val_f1 = test(val_loader)
test_f1 = test(test_loader)
print(f'Epoch: {epoch:02d}, 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")
|
