Knowledge graphs (dglke)

Hi,
Tried knowledge graphs with FB15k dataset and tried finding the similarity embeddings with the following code
!DGLBACKEND=pytorch dglke_emb_sim --emb_file ‘/content/ckpts/TransE_l2_FB15k_0/FB15k_TransE_l2_entity.npy’ --format ‘l_r’ --data_files ‘/content/drive/My Drive/Amazon ml/head.txt’ ‘/content/drive/My Drive/Amazon ml/relation.txt’ --topK 5
I am getting the following error for finding the links and similar embeddings
RuntimeError: Integer division of tensors using div or / is no longer supported, and in a future release div will perform true division as in Python 3. Use true_divide or floor_divide (// in Python) instead
Please do tell what can be done

Which python version are you using?
And what kind environment you are using?
Are you using python2? Currently DGL-KE only work with python3

Was trying in colab,python 3, dgl 0.4.3 as it told only this was compatible with dglke.
Have posted the exact code,last two lines are showing the said error:
!sudo pip3 install dgl==0.4.3
!sudo pip3 install dglke

!DGLBACKEND=pytorch dglke_train --model_name TransE_l2 --dataset FB15k --batch_size 1000
–neg_sample_size 200 --hidden_dim 400 --gamma 19.9 --lr 0.25 --max_step 500 --log_interval 100
–batch_size_eval 16 -adv --regularization_coef 1.00E-09 --test --num_thread 1 --num_proc 8

!DGLBACKEND=pytorch dglke_eval --model_name TransE_l2 --dataset FB15k --hidden_dim 400 --gamma 19.9 --batch_size_eval 16
–num_thread 1 --num_proc 8 --model_path ‘/content/ckpts/TransE_l2_FB15k_0’

Using PyTorch Backend

!DGLBACKEND=pytorch dglke_predict --model_path ‘/content/ckpts/TransE_l2_FB15k_0’ --format ‘h_r_t’ --data_files ‘/content/drive/My Drive/Amazon ml/head.txt’ ‘/content/drive/My Drive/Amazon ml/relation.txt’ ‘/content/drive/My Drive/Amazon ml/tail.txt’ --score_func logsigmoid --topK 5 --exec_mode ‘batch_head’

Using PyTorch Backend

!DGLBACKEND=pytorch dglke_emb_sim --emb_file ‘/content/ckpts/TransE_l2_FB15k_0/FB15k_TransE_l2_entity.npy’ --format ‘l_r’ --data_files ‘/content/drive/My Drive/Amazon ml/head.txt’ ‘/content/drive/My Drive/Amazon ml/relation.txt’ --topK 5

This maybe a compatibility problem. For pytorch 1.6, it will not support certain div: https://pytorch.org/docs/stable/generated/torch.div.html

Can you try it with pytorch 1.5 and help us raise a issue in https://github.com/awslabs/dgl-ke/issues?

Worked with pytorch 1.5. Thanks for the help