Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Graph Sage OGBN Example with Perforated Backpropagation #9877

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Graph Sage OGBN Example with Perforated Backpropagation #9877

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1157d80
checking in graphSage example original file from the branch I was usi…
RorryB Dec 17, 2024
7446d41
removed PAI and _original from first PR. moved _scheduler to replace…
RorryB Dec 18, 2024
6f66d89
rebase with master
RorryB Dec 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion examples/ogbn_train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@
action='store_true',
help='Whether or not to use GAT model',
)
parser.add_argument('-e', '--epochs', type=int, default=10)
parser.add_argument('-e', '--epochs', type=int, default=50)
parser.add_argument('--num_layers', type=int, default=3)
parser.add_argument('--num_heads', type=int, default=2,
help='number of heads for GAT model.')
Expand Down Expand Up @@ -179,6 +179,7 @@ def test(loader: NeighborLoader) -> float:
lr=args.lr,
weight_decay=args.wd,
)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max',patience=5)

print(f'Total time before training begins took '
f'{time.perf_counter() - wall_clock_start:.4f}s')
Expand All @@ -204,6 +205,10 @@ def test(loader: NeighborLoader) -> float:
if val_acc > best_val:
best_val = val_acc
times.append(time.perf_counter() - train_start)
for param_group in optimizer.param_groups:
print('lr:')
print(param_group['lr'])
scheduler.step(val_acc)

print(f'Average Epoch Time on training: '
f'{torch.tensor(train_times).mean():.4f}s')
Expand Down
Loading