how to change to Microsoft.ML.OnnxRuntime.Tensors.DenseTensor<float>?
Open
Nobody has claimed this yet.
- Dominant language
- C#
- Stars
- 1.5k
- Forks
- 205
- Avg merge
- 7d 7h
- Merged PRs (30d)
- 2
Description
public static void ExtractPixelsArgb(DenseTensor tensor, Span data, int pixelCount)
{
Span spanR = tensor.Buffer.Span;
Span spanG = spanR[pixelCount..];
Span spanB = spanG[pixelCount..];
int sidx = 0;
for (int i = 0; i < pixelCount; i++)
{
spanR[i] = data[sidx + 2] * 0.0039215686274509803921568627451f;
spanG[i] = data[sidx + 1] * 0.0039215686274509803921568627451f;
spanB[i] = data[sidx] * 0.0039215686274509803921568627451f;
sidx += 4;
}
}
Is there a faster way than this?
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 with the ExtractPixelsArgb entry point and the DenseTensor buffer operations shown in the issue. Profile the current loop and investigate whether the tensor and span usage has a faster supported approach; done means demonstrating an equivalent result with measurable improvement.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- csharp
- Domain
- machine-learning, performance
- Issue type
- Refactor
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100