Skip to content
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

loss is negative when trianing the flow model using a pointcloud autoencoder #15

Open
L-Aidan opened this issue Nov 24, 2022 · 2 comments
Open

loss is negative when trianing the flow model using a pointcloud autoencoder #15

L-Aidan opened this issue Nov 24, 2022 · 2 comments

Comments

@L-Aidan
Copy link

L-Aidan commented Nov 24, 2022 •
edited
Loading

I found the logdet becomes 200+ after the first batchnormFlow model, is this related with the input of the flow model(the output of the autoencoder)?
@L-Aidan L-Aidan changed the title loss is negative loss is negative when trianing the flow model using a pointcloud autoencoder Nov 24, 2022
@L-Aidan
Copy link
Author

L-Aidan commented Nov 25, 2022

I found the loss would be negative even when training the voxel with pretrained ckpt. Does anyone else meet this problem?

@happysxpp
Copy link

the same problem

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@L-Aidan @happysxpp