DeepGraphLearning / KnowledgeGraphEmbedding

MIT License
1.24k stars 264 forks source link

Can't find log files #25

Closed p6jain closed 4 years ago

p6jain commented 4 years ago

Hi!

I trained the model using the following command:

CUDA_VISIBLE_DEVICES=0 python -u codes/run.py --do_train --cuda --do_valid --do_test --data_path data/FB15k-237 --model RotatE -n 256 -b 1024 -d 1000 -g 24.0 -a 1.0 -adv -lr 0.0001 --max_steps 150000 **-save models/RotatE_FB15k-237** --test_batch_size 16 -de --cuda

and tested it using:

time CUDA_VISIBLE_DEVICES=1 python -u codes/run.py --do_test -init models/RotatE_FB15k-237/ --cuda  

I am not able to find the log files in models/RotatE_FB15k-237/ folder. I am unsure what went wrong. Please help.

Edward-Sun commented 4 years ago

Hi Prachi,

Can you find the model checkpoint in models/RotatE_FB15k-237 directory before testing?

p6jain commented 4 years ago

Yes, there is one.

Edward-Sun commented 4 years ago

Hi Prachi,

I have no idea. Could you please try:

CUDA_VISIBLE_DEVICES=1 python -u codes/run.py --do_test -init models/RotatE_FB15k-237/ --cuda

without time again?

If it doesn't work, you can upload your checkpoint and I'll try to figure out the problem.