I am trying to replicate user defined KG training command but giving me below exception. I am a beginner user so I am lost on the way now
this is what I run in python
import subprocess
subprocess.run(["dglke_train","--model_name", "TransE_l2",\
"--batch_size", "1000",\
"--neg_sample_size", "200", \
"--hidden_dim", "400", \
"--gamma", "19.9", \
"--lr", "0.25", \
"--max_step", "24000", \
"--log_interval", "100", \
"--batch_size_eval", "16", \
"-adv", \
"--regularization_coef", "1.00E-09", \
"--gpu", "0", \
"--save_path", "./data", \
"--data_path", "./dataset/", \
"--format", "raw_udd_hrt", \
"--data_files", "train.tsv", \
"--dataset", "xxx",\
"--neg_sample_size_eval", "10000"
], stdout=subprocess.PIPE)
train.tsv is looking like below tab seperated head realtion tail file
Beijing is_capital_of China
Pairs is_capital_of France
London is_capital_of UK
UK located_at Europe
China located_at Asia
Tokyo is_capital_of Japan
the error is below
File “c:\users\umitozm\anaconda3\lib\site-packages\dgl\utils\internal.py”, line 58, in _dispatch
raise InconsistentDtypeException(‘Index data specified as %s, but got: %s’ %
dgl.utils.internal.InconsistentDtypeException: DGL now requires the input tensor to have the same dtype as the graph index’s dtype(which you can get by g.idype). Index data specified as int64, but got: int32