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.

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

Update hourglass models (or make a new one?) to be base on smallest of input/output #399

Open
milesgranger opened this issue Aug 12, 2019 · 1 comment

Comments

@milesgranger
Copy link
Contributor

Here there is definitely kind of an issue. If you run hourglass with 40 features in, 20 out and compression_factor=0.5, how small would you expect the smallest layer to be? Today it will be 20, so the 20 out nodes can be pushed right through. To me it definitely seems reasonable to have the compression-factor multiply the smallest of in and out-nodes. But some care must (maybe) be taken in ensuring that it has the right nr of in-neurons as well, and that the slope from 40 to the smallest layer of 10 is reasonable, and that the slope from 10 to 20 is reasonable. It can definitely no longer use lstm_symmetric directly:-p

#368 (comment)

@flikka flikka changed the title Update hourglass models to be base on smallest of input/output Update hourglass models (or make a new one?) to be base on smallest of input/output Oct 15, 2019
@flikka
Copy link
Contributor

flikka commented Oct 15, 2019

Maybe the hourglass is not the right one for these types of models. Maybe not even a symmetric one.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants