microsoft / microsoft/onnxruntime
[Feature Request] Onnxruntime-gpu for SwinTransformer
Open
Nobody has claimed this yet.
feature request
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
Describe the feature request
When I test onnx model of swin transformer by utilizing onnxruntime-gpu and torch model on GPU, I found the latency is 35ms vs 36ms per image.
Describe scenario use case
pytorch Swin Transformer inference
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.
Research direction
Start by reproducing the reported Swin Transformer inference comparison using onnxruntime-gpu and the PyTorch model on a GPU, measuring the stated 35 ms versus 36 ms latency. The issue does not identify files, tests, an entry point, or a specific change, so the expected implementation and completion criteria require clarification.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, pytorch
- Domain
- machine-learning, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100