mando-project / ge-sc Goto Github PK

python -m experiments.graph_classification --epochs 50 --repeat 20

This command cannot be run

Can you please tell me how the data in the experiments/ge-sc-data/source_code/gesc_matrices_node_embedding folder is generated?

When I run python -m experiments.graph_classification --epochs 50 --repeat 20, it reports error
Missing files, is it a problem with the code or is the dataset incomplete?
The error is reported as：
No such file or directory: './experiments/ge-sc-data/byte_code/smartbugs/runtime/gpickles/gesc_matrices_node_embedding/balanced/matrix_line_dim128_of_core_graph_of_access_control_runtime_balanced_cfg_cg_compressed_graphs.pkl'

The error is:

dgl._ffi.base.DGLError: Cannot assign node feature "feat" on device cpu to a graph on device cuda:0. Call DGLGraph.to() to copy the graph to the same device.

when I run graph classification.

Hello, I am not sure whether it is caused by the environment problem or the failure to upload your last code update. I followed the require prompt in README and installed the environment, but there are some errors in running the following commands. Here's an example. My environment, called MANDO, runs commands that are copied directly.

=======================================================================
(MANDO) astronaut@dell-PowerEdge-T640:/data/space_station/ge-sc$ python node_classifier.py -ld ./logs/node_classification/cfg/gae/access_control --output_models ./models/node_classification/cfg/gae/access_control --dataset ./experiments/ge-sc-data/source_code/access_control/buggy_curated/ --compressed_graph ./experiments/ge-sc-data/source_code/access_control/buggy_curated/cfg_compressed_graphs.gpickle --node_feature gae --feature_extractor ./experiments/ge-sc-data/source_code/gesc_matrices_node_embedding/matrix_gae_dim128_of_core_graph_of_access_control_cfg_buggy_curated.pkl --testset ./experiments/ge-sc-data/source_code/access_control/curated --seed 1
Using backend: pytorch
Training phase
Getting features
Traceback (most recent call last):
File "node_classifier.py", line 240, in
train_results, val_results = main(args)
File "node_classifier.py", line 56, in main
model = MANDONodeClassifier(args['compressed_graph'], feature_extractor=feature_extractor, node_feature=args['node_feature'], device=device)
TypeError: init() missing 1 required positional argument: 'source_path'