tensorflow / tensorflow/models
VGGish / YAMNet support for batch inference
Open
Nobody has claimed this yet.
models:research
type:feature
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
source
https://github.com/tensorflow/models/tree/master/research/audioset/vggish
request
Would it be possible to add a method to a VGGish model loaded from tensorhub to allow batch inference?
Additional context
I am running this on millions of songs. I am also considering Ray or Apache beam to parallelize, but I assume it would be more efficient to allow the tensors themselves to accept batches. I am willing to contribute.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.