You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: benchmarking/README.md
-4Lines changed: 0 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,7 +1,3 @@
1
-
# benchmarking
2
-
3
-
This directory contains files used for validating the parallel implementation and benchmarking key operations.
4
-
5
1
## Files
6
2
7
3
-**pyg_serial.py**: This Python script provides a serial implementation of a GNN model using PyTorch Geometric (PyG). It is primarily used for validation purposes, allowing for comparison against the parallelized version. The script is configured to train a model with 3 Graph Convolutional Network (GCN) layers and a hidden dimension size of 128 on the ogbn-products dataset by default.
0 commit comments