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

[Relay] Support for GroupNorm #5278

Closed
NarendraPatwardhan opened this issue Apr 8, 2020 · 1 comment
Closed

[Relay] Support for GroupNorm #5278

NarendraPatwardhan opened this issue Apr 8, 2020 · 1 comment

Comments

@NarendraPatwardhan
Copy link

Many modern models utilize GroupNorm, there is support for LayerNorm and InstanceNorm under tvm/relay/op/nn. It is especially helpful for training with low number of samples and more efficient than instance norm in terms of parameters. It would be valuable addition to add it to core set of operators as libraries like pytorch or mxnet already support it.

@masahi
Copy link
Member

masahi commented Apr 17, 2020

#5358

@masahi masahi closed this as completed Apr 17, 2020
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