zehao-dong / cktgnn Goto Github PK

Thanks for your excellent work. But when I try to get the whole dataset. I find that the conversion of .pkl files to circuit netlist is a little bit confusing. Should I use the script "/src/graph_to_fom" or something else? Meanwhile, I wonder the difference among ckt_benck_101_pygraph.pkl, ckt_benck_101_tensor.pkl, and ckt_benck_101.pkl

(base) PS C:\Users\Qingbolan\Desktop\6004_cktgnn_circuit_graph_neural_ne-Supplementary Material\Supplementary_material\raw_code> python train_simple.py --data-name circuit101 --save-interval 100 --save-appendix _CVAE --epochs 300 --lr 1e-4 --model CVAE --nz 64 --batch-size 64 --ng 10000 --cuda_id 0 --hs 606
E:\develop\Python\Ananconda\lib\site-packages\torchvision\io\image.py:13: UserWarning: Failed to load image Python extension: '[WinError 127] 找不到指定的程序。'If you don't plan on using image functionality from torchvision.io, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have libjpeg or libpng installed before building torchvision from source?
warn(
Namespace(data_name='circuit101', nvt=26, max_n=8, subg_nvt=10, subn_nvt=10, ng=10000, node_feat_type='discrete', save_appendix='_CVAE', save_interval=100, sample_number=20, no_test=False, reprocess=False, keep_old=False, only_test=False, model='CVAE', load_latest_model=False, continue_from=None, emb_dim=128, hs=606, nz=64, bidirectional=False, lr=0.0001, epochs=300, batch_size=64, cuda_id=0, infer_batch_size=128, no_cuda=False, all_gpus=False, seed=1, predictor=False, cuda=False)
0%| | 0/10000 [00:00<?, ?it/s]
Traceback (most recent call last):
File "C:\Users\Qingbolan\Desktop\6004_cktgnn_circuit_graph_neural_ne-Supplementary Material\Supplementary_material\raw_code\train_simple.py", line 147, in
train_dataset, test_dataset = train_test_generator_topo_simple(ng=args.ng, name=txt_name)
File "C:\Users\Qingbolan\Desktop\6004_cktgnn_circuit_graph_neural_ne-Supplementary Material\Supplementary_material\raw_code\utils.py", line 302, in train_test_generator_topo_simple
subg_type = int(row[0])
IndexError: list index out of range