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

Implement RandomUniform operator #69

Merged
merged 3 commits into from
Mar 30, 2024
Merged

Implement RandomUniform operator #69

merged 3 commits into from
Mar 30, 2024

Conversation

robertknight
Copy link
Owner

@robertknight robertknight commented Mar 29, 2024

Implemented as part of getting Tacotron2 to work. See https://github.com/robertknight/xd-tts/tree/rten-inference.

  • Use a unique seed in each thread (resolved by using fastrand as the rng)

When loading a model with an operator that is supported by RTen but not enabled
for the current model or rten crate features, include the name of the operator
in the error. This makes rectifying the problem much easier.
This adds a new dependency on fastrand. Most models won't need random number
generation operators, so make this an optional feature.
@robertknight robertknight marked this pull request as ready for review March 30, 2024 07:45
@robertknight robertknight merged commit 864b78a into main Mar 30, 2024
2 checks passed
@robertknight robertknight deleted the random-uniform branch March 30, 2024 07:45
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

Successfully merging this pull request may close these issues.

1 participant