microsoft / microsoft/onnxruntime
Is OnnxRt support sparse tensor input?
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
I'm wonder if onnxruntime support input a sparse tensor like scipy.sparse or torch.sparse.FloatTensor?
or if onnxruntime has a switch to open sparse tensor, like expand a tensor from (1,n) to (k,n), the memory doesn't expand k times.
- ONNX Runtime version (you are using): 1.4.0
support of sparse tensor in 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
The issue names ONNX Runtime 1.4.0 and asks about sparse inputs from scipy.sparse or torch.sparse.FloatTensor, but it does not identify a file, entry point, or test. Start by locating ONNX Runtime's inference input and tensor representation code, then check existing sparse-tensor coverage. Done means the supported behavior and any required implementation scope are documented or tested.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100