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

Shouldn't z be a Gaussian distribution? seems that in code your code you just take out the output of a hidden layer (train_z) and then you minimize the MMD of that with a prior! #3

Closed
AliLotfi92 opened this issue Jun 20, 2019 · 3 comments
Closed

Shouldn't z be a Gaussian distribution? seems that in code your code you just take out the output of a hidden layer (train_z) and then you minimize the MMD of that with a prior! #3

AliLotfi92 opened this issue Jun 20, 2019 · 3 comments

Comments

@AliLotfi92
Copy link

No description provided.

@AliLotfi92 AliLotfi92 changed the title Shouldn't z be a Gaussian distribution? seems that in code your code you just take out the output of a hidden layer (train_z) and then you minimize the distance MMD of that with a prior! Shouldn't z be a Gaussian distribution? seems that in code your code you just take out the output of a hidden layer (train_z) and then you minimize the MMD of that with a prior! Jun 26, 2019
@rojinsafavi
Copy link

Did you figure this out?

@AliLotfi92
Copy link
Author

Nope, a similar issue is still open here:
https://github.com/ShengjiaZhao/InfoVAE/issues/1
I should say I've not been able to reproduce the reported results after fixing this. I have the fixed version, let me know if you need that.

@AliLotfi92 AliLotfi92 reopened this Nov 16, 2019
@ShengjiaZhao
Copy link
Owner

Hi sorry for this late reply. I haven't been up to date on looking at this repo. In the tutorial, we use a simplified implementation without adding random noise. For the version with random noise please see this file
https://github.com/ShengjiaZhao/MMD-Variational-Autoencoder/blob/master/mmd_vae_eval.py

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
3 participants
@ShengjiaZhao @rojinsafavi @AliLotfi92