LMSupply.Segmenter
0.125.0
dotnet add package LMSupply.Segmenter --version 0.125.0
NuGet\Install-Package LMSupply.Segmenter -Version 0.125.0
<PackageReference Include="LMSupply.Segmenter" Version="0.125.0" />
<PackageVersion Include="LMSupply.Segmenter" Version="0.125.0" />
<PackageReference Include="LMSupply.Segmenter" />
paket add LMSupply.Segmenter --version 0.125.0
#r "nuget: LMSupply.Segmenter, 0.125.0"
#:package LMSupply.Segmenter@0.125.0
#addin nuget:?package=LMSupply.Segmenter&version=0.125.0
#tool nuget:?package=LMSupply.Segmenter&version=0.125.0
LMSupply.Segmenter
Local image segmentation for .NET with automatic model downloading.
Features
- Zero-config: Models download automatically from HuggingFace
- GPU Acceleration: CUDA (NVIDIA), CoreML (macOS)
- MIT Licensed: SegFormer models for commercial use
- 150 ADE20K Classes: Indoor/outdoor scene understanding
Quick Start
using LMSupply.Segmenter;
// Load the default model
await using var segmenter = await LocalSegmenter.LoadAsync("default");
// Segment image
var result = await segmenter.SegmentAsync("photo.jpg");
Console.WriteLine($"Image: {result.Width}x{result.Height}");
Console.WriteLine($"Classes found: {result.UniqueClassCount}");
// Get class at pixel
int classId = result.GetClassAt(100, 100);
Console.WriteLine($"Class at (100,100): {segmenter.ClassLabels[classId]}");
Available Models
| Alias | Model | Size | mIoU | Description |
|---|---|---|---|---|
default |
SegFormer-B0 | ~15MB | 38.0 | Lightweight, fast |
fast |
SegFormer-B1 | ~55MB | 42.2 | Balanced |
quality |
SegFormer-B2 | ~110MB | 46.5 | Higher accuracy |
large |
SegFormer-B5 | ~340MB | 51.0 | Highest accuracy |
interactive |
MobileSAM | ~45MB | - | Point/box prompts — LocalSegmenter.LoadInteractiveAsync() |
GPU Acceleration
Do not add ONNX Runtime packages (Microsoft.ML.OnnxRuntime*): LMSupply provisions the runtime itself, and a
second copy conflicts with it. ExecutionProvider.Auto uses CUDA when the driver supports CUDA 13 and the CUDA 13
runtime and cuDNN 9 are installed on the machine (ONNX Runtime 1.30 is built for CUDA 13), CoreML on macOS, and the CPU otherwise. On Windows with an AMD or Intel GPU, ONNX
sessions run on the CPU (DirectML was removed in 0.67.0). See
GPU acceleration.
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net10.0 is compatible. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
-
net10.0
- LMSupply.Core (= 0.125.0)
- LMSupply.Vision.Core (= 0.125.0)
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.
| Version | Downloads | Last Updated |
|---|---|---|
| 0.125.0 | 0 | 10/17/2026 |
| 0.124.0 | 0 | 10/17/2026 |
| 0.123.0 | 39 | 10/16/2026 |
| 0.122.0 | 56 | 10/15/2026 |
| 0.121.0 | 48 | 10/14/2026 |
| 0.120.0 | 91 | 10/12/2026 |
| 0.119.0 | 85 | 10/12/2026 |
| 0.118.0 | 92 | 10/11/2026 |
| 0.117.1 | 95 | 10/11/2026 |
| 0.117.0 | 95 | 10/11/2026 |
| 0.116.0 | 86 | 10/11/2026 |
| 0.115.1 | 102 | 10/8/2026 |
| 0.115.0 | 90 | 10/8/2026 |
| 0.114.0 | 90 | 10/8/2026 |
| 0.113.0 | 93 | 10/8/2026 |
| 0.112.1 | 84 | 10/7/2026 |
| 0.112.0 | 92 | 10/7/2026 |
| 0.111.0 | 83 | 10/7/2026 |
| 0.110.1 | 92 | 10/7/2026 |
| 0.110.0 | 84 | 10/7/2026 |