-
Notifications
You must be signed in to change notification settings - Fork 2k
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.
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
Questions about parallel SPPE? #37
Comments
To calculate the loss between the center-located ground truth poses and the output, we use the same loss as the main SPPE. |
So what if I discard the parallel SPPE and just use the main branch?Should I add a new loss or just train the net as before(with stn but without parallel SPPE)? @Fang-Haoshu |
you can train it as before, but a question is why you want to do that.. |
emmm...poor gpu memory? |
Oh I see, then you may try using a smaller batch size and enlarge the iter_size. Refer to the opt.lua |
Thanks for replying! |
Hey,in the parallel SPPE branch,how to calculate the loss between the center-located ground truth poses and the output?And how to make the center-located ground truth pose image?Is it just cropped from the origin image?
The text was updated successfully, but these errors were encountered: