Open OGWang126 opened 4 years ago
when I try to run the train_embeddings.ipynb code. the command not found. And here are my code
print(os.system("DGLBACKEND=pytorch dglke_train --dataset DRKG --data_path ./train --data_files drkg_train.tsv drkg_valid.tsv drkg_test.tsv --format 'raw_udd_hrt' --model_name TransE_l2 --batch_size 2048 "))
print(os.system('--neg_sample_size 256 --hidden_dim 400 --gamma 12.0 --lr 0.1 --max_step 100000 --log_interval 1000 --batch_size_eval 16 -adv --regularization_coef 1.00E-07 --test --num_thread 1 --gpu 0 1 2 3 4 5 6 7 --num_proc 8 --neg_sample_size_eval 10000 --async_update'))
And the error remind
sh: dglke_train: command not found 32512 sh: --: invalid option Usage: sh [GNU long option] [option] ... sh [GNU long option] [option] script-file ...
thanks
Did you do
!pip3 install torch !pip3 install dgl !pip3 install dglke
What kind of machine you are using?
when I try to run the train_embeddings.ipynb code. the command not found. And here are my code
print(os.system("DGLBACKEND=pytorch dglke_train --dataset DRKG --data_path ./train --data_files drkg_train.tsv drkg_valid.tsv drkg_test.tsv --format 'raw_udd_hrt' --model_name TransE_l2 --batch_size 2048 "))
print(os.system('--neg_sample_size 256 --hidden_dim 400 --gamma 12.0 --lr 0.1 --max_step 100000 --log_interval 1000 --batch_size_eval 16 -adv --regularization_coef 1.00E-07 --test --num_thread 1 --gpu 0 1 2 3 4 5 6 7 --num_proc 8 --neg_sample_size_eval 10000 --async_update'))
And the error remind
sh: dglke_train: command not found 32512 sh: --: invalid option Usage: sh [GNU long option] [option] ... sh [GNU long option] [option] script-file ...
thanks