-
Notifications
You must be signed in to change notification settings - Fork 31
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
ellipsoid_cut model shows poor correspondence #1104
Comments
Will be fixed for release via issue #1133 |
@HeavenlyBerserker After updating the ellipsoid data to only have one mode of variation I am still seeing bad correspondence. The shape model correctly predicts only one mode of variation but some of the particles are crossing over each other. |
@jadie1 I'll look at it on Thursday. Thanks for the note. |
@HeavenlyBerserker @jadie1 is this issue resolved? |
To the best of my knowledge, yes. |
The PR is using the old data still, it should be using ellipsoid_1mode_aligned. I am still seeing particles switch when the iterations are increased. I have tried a lot of different params and have had no luck so far... |
That was with 128 particles though. I will test with the new params on the one_mode_ellipsoid branch which uses the new data. If that looks good then we can close this |
Here's what I see at the end of ellipsoid_cut. Notice there are swapped particles, etc.
Ellipsoid_Cut.mp4
The text was updated successfully, but these errors were encountered: