search

askforalfred / alfred

ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
MIT License
360 stars 77 forks source link

Question regarding speed with multiple instances of AI2THOR #77

Closed soyeonm closed 3 years ago

soyeonm commented 3 years ago

Hello,

I have a question regarding the number of threads (the number of instances of AI2THOR's controller). I saw that in the commands provided in your "models" folder, the "num_threads" are 3. e.g.

$ python models/eval/eval_seq2seq.py --model_path /best_seen.pth --eval_split valid_seen --data data/json_feat_2.1.0 --model models.model.seq2seq_im_mask --gpu --num_threads 3

I observed that on my server, any number of thread (or any simultaneously running instances of AI2THOR) beyond 3 makes the entire computer very, very slow.

Do you have an insight on how to overcome such an issue? Or is this also why the num_threads is "3" for your example command as well?

Thanks all the time.

MohitShridhar commented 3 years ago

@soyeonm num_threads is the number of parallel instances of THOR to run. The higher the number, the faster the evaluation. For faster speed you need a machine with more CPUs+RAM.