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

Fix np.memmap usage, add flag to force not using memmap #2081

Merged
merged 1 commit into from
Feb 3, 2025
Merged

Fix np.memmap usage, add flag to force not using memmap #2081

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 11 additions & 11 deletions graph/R-GAT/tools/accuracy_igbh.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,10 @@ def get_args():
default="full",
choices=["tiny", "small", "medium", "large", "full"]
)
parser.add_argument(
"--no-memmap",
action="store_true",
help="do not use memmap even for large/full size variants")
parser.add_argument(
"--verbose",
action="store_true",
Expand All @@ -38,7 +42,7 @@ def get_args():
return args


def load_labels(base_path, dataset_size, use_label_2K=True):
def load_labels(base_path, dataset_size, use_label_2K=True, no_memmap=False):
# load labels
paper_nodes_num = {
"tiny": 100000,
Expand All @@ -57,16 +61,12 @@ def load_labels(base_path, dataset_size, use_label_2K=True):
"paper",
label_file)

if dataset_size in ["large", "full"]:
paper_node_labels = torch.from_numpy(
np.memmap(
paper_lbl_path, dtype="float32", mode="r", shape=(paper_nodes_num[dataset_size])
)
).to(torch.long)
if dataset_size in ["large", "full"] and not no_memmap:
mmap_mode = 'r'
else:
paper_node_labels = torch.from_numpy(
np.load(paper_lbl_path)).to(
torch.long)
mmap_mode = None

paper_node_labels = torch.from_numpy(np.load(paper_lbl_path, mmap_mode=mmap_mode)).to(torch.long)
labels = paper_node_labels
val_idx = torch.load(
os.path.join(
Expand All @@ -92,7 +92,7 @@ def get_labels(labels, val_idx, id_list):
with open(args.mlperf_accuracy_file, "r") as f:
mlperf_results = json.load(f)

labels, val_idx = load_labels(args.dataset_path, args.dataset_size)
labels, val_idx = load_labels(args.dataset_path, args.dataset_size, no_memmap=args.no_memmap)
results = {}

seen = set()
Expand Down
Loading