DeepMimic
DeepMimic copied to clipboard
Limit samples for training
is there any way to make the training stop after N samples/iterations?
That's not implemented at the moment. But it should be pretty easy to just modify the done
variable here:
https://github.com/xbpeng/DeepMimic/blob/c0731625e72c96a3f758def75f5e4ecbf60e8ca1/DeepMimic_Optimizer.py#L16
To check if the total number of samples exceeds some limit.
Thanks! I will try to take a look. So right now what's the criterion for done
?
done is just always false right now.