The parameter value of pose_mimic_eval.py

[gyou2021]

Hi,
In imitator/script-summary-gt2d-v5.sh,
159 >> inference the RL result using trained model
160 python pose_imitation/pose_mimic_eval.py --cfg subject_h36mrib --data train --num-threads 52 --iter 1200 .....
Why 1200 was selected for --iter? How to select the value? Thank you!

[Garfield-kh]

Hi, thank you for the interest!
in this part, you can see that I use the this line 157 to copy the previous RL training weight to here and rename it as iter_100.p as a pretraining.
In this way, the training iteration can be reduced.
This can be verified by looking at the tensorboard training curve, the total reward.
1200 is set for one night training, I also tried 2400, 3000, 6000, they produce similar result.

[gyou2021]

Thank you for your reply!