New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

what is the batch size for the sampling? #107

Open

JiahaoYao opened this issue Sep 18, 2019 · 2 comments

JiahaoYao commented Sep 18, 2019

Hi,

When I look into the sampling code here: https://github.com/melodyguan/enas/blob/master/src/cifar10/general_controller.py#L127-L268, I find that it does not contains batch size. I mean without batch size it is really hard to optimize by policy gradient method. Could anyone tell me whether I understand correctly. Is here the training is batchsize=1?

pingguokiller commented Oct 30, 2019

batchsize is set in the script.

Author

JiahaoYao commented Dec 16, 2019 •

edited

Loading

I think the batch_size in the script indicates that for training the child_model, as shown in https://github.com/melodyguan/enas/blob/master/src/ptb/main.py#L114. Actually, I mean the batchsize for the policy gradient. I think in the https://github.com/melodyguan/enas/blob/master/src/ptb/main.py#L311-L320, the batchsize should be 1, right?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment