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

spasity function only work on keras sequential model/layer? #78

Closed
Charlie4zc opened this issue Aug 21, 2019 · 2 comments
Closed

spasity function only work on keras sequential model/layer? #78

Charlie4zc opened this issue Aug 21, 2019 · 2 comments
Assignees
Labels
technique:pruning Regarding tfmot.sparsity.keras APIs and docs

Comments

@Charlie4zc
Copy link

Since i'd like to use sparsity.keras.prune_low_magnitude on my model and failed due to unknown reason, i was wondering whether it only work on keras sequential models?
BTW my keras model has a lot skip connections , so i can only apply on pretrained models(which it works)or sequential 'block's of my model?

@alanchiao
Copy link

alanchiao commented Oct 21, 2019

It currently works on sequential and functional models, though it'll throw an error for subclassed models. It'd be good to update the docs to clarify this also.

Assigning to self since I'm working on initial subclassed model support.

@alanchiao alanchiao self-assigned this Oct 21, 2019
@alanchiao
Copy link

Closing now.

If you're interested in subclassed model support, see this issue.

@alanchiao alanchiao added the technique:pruning Regarding tfmot.sparsity.keras APIs and docs label Feb 6, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
technique:pruning Regarding tfmot.sparsity.keras APIs and docs
Projects
None yet
Development

No branches or pull requests

2 participants