My working environment is as follows: gtx 1650 ×1 core i7-9700 ×1 tensorf

I think you may put command like <div class="snippet-clipboard-content notranslate

run the script showed in start.sh but failed。 about impala-distributed-tensorflow HOT 3 OPEN

rlopensource commented on May 29, 2024

run the script showed in start.sh but failed。

from impala-distributed-tensorflow.

Comments (3)

chagmgang commented on May 29, 2024

I think you may put command like

sh start.sh

But I consider that you have to command like

nohup sh start.sh

Thank you.

from impala-distributed-tensorflow.

sunchipsster1 commented on May 29, 2024

Hello! I also ran into this problem. I ran the code for 24 hours on a gpu server and output = CreateSession still waiting for response from worker: /job:actor/replica:0/task:17... etc. was present the whole time. Does anyone know how to fix this? Thanks for the kind help!

from impala-distributed-tensorflow.

chagmgang commented on May 29, 2024

I think you maybe not running 17th actor task.
Rerun the 17th task by command

python trainer_invader.py --num_actors=32 --task=17 --batch_size=32 --queue_size=128 --trajectory=20 --learning_frame=1000000000 --start_learning=0.0006 --end_learning=0.0 --discount_factor=0.99 --entropy_coef=0.05 --baseline_loss_coef=1.0 --gradient_clip_norm=40.0 --job_name=actor --reward_clipping=abs_one --lstm_size=256 &

from impala-distributed-tensorflow.

Recommend Projects