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
|
import argparse
import os.path as osp
import time
import torch
import torch.nn.functional as F
import torch_geometric
import torch_geometric.transforms as T
from torch_geometric.datasets import Planetoid
from torch_geometric.logging import init_wandb, log
from torch_geometric.nn import GATConv
parser = argparse.ArgumentParser()
parser.add_argument('--dataset', type=str, default='Cora')
parser.add_argument('--hidden_channels', type=int, default=8)
parser.add_argument('--heads', type=int, default=8)
parser.add_argument('--lr', type=float, default=0.005)
parser.add_argument('--epochs', type=int, default=200)
parser.add_argument('--wandb', action='store_true', help='Track experiment')
args = parser.parse_args()
if torch.cuda.is_available():
device = torch.device('cuda')
elif torch_geometric.is_xpu_available():
device = torch.device('xpu')
else:
device = torch.device('cpu')
init_wandb(name=f'GAT-{args.dataset}', heads=args.heads, epochs=args.epochs,
hidden_channels=args.hidden_channels, lr=args.lr, device=device)
path = osp.join(osp.dirname(osp.realpath(__file__)), '..', 'data', 'Planetoid')
dataset = Planetoid(path, args.dataset, transform=T.NormalizeFeatures())
data = dataset[0].to(device)
class GAT(torch.nn.Module):
def __init__(self, in_channels, hidden_channels, out_channels, heads):
super().__init__()
self.conv1 = GATConv(in_channels, hidden_channels, heads, dropout=0.6)
# On the Pubmed dataset, use `heads` output heads in `conv2`.
self.conv2 = GATConv(hidden_channels * heads, out_channels, heads=1,
concat=False, dropout=0.6)
def forward(self, x, edge_index):
x = F.dropout(x, p=0.6, training=self.training)
x = F.elu(self.conv1(x, edge_index))
x = F.dropout(x, p=0.6, training=self.training)
x = self.conv2(x, edge_index)
return x
model = GAT(dataset.num_features, args.hidden_channels, dataset.num_classes,
args.heads).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.005, weight_decay=5e-4)
def train():
model.train()
optimizer.zero_grad()
out = model(data.x, data.edge_index)
loss = F.cross_entropy(out[data.train_mask], data.y[data.train_mask])
loss.backward()
optimizer.step()
return float(loss)
@torch.no_grad()
def test():
model.eval()
pred = model(data.x, data.edge_index).argmax(dim=-1)
accs = []
for mask in [data.train_mask, data.val_mask, data.test_mask]:
accs.append(int((pred[mask] == data.y[mask]).sum()) / int(mask.sum()))
return accs
times = []
best_val_acc = final_test_acc = 0
for epoch in range(1, args.epochs + 1):
start = time.time()
loss = train()
train_acc, val_acc, tmp_test_acc = test()
if val_acc > best_val_acc:
best_val_acc = val_acc
test_acc = tmp_test_acc
log(Epoch=epoch, Loss=loss, Train=train_acc, Val=val_acc, Test=test_acc)
times.append(time.time() - start)
print(f"Median time per epoch: {torch.tensor(times).median():.4f}s")
|