tensorflow / tensorflow/models
Deeplab model run on GPU
Open
@aquariusjay is already working on this.
Since Aug 3, 2021.
models:research
type:support
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
When I convert deeplab graph to tflite, it contains these two operations and GPU doesn't support these two ops
BatchToSpaceNd
SpaceToBatchNd
I find one solution in #7953
I try to set output-stride=32, but it still not work
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.