YOLO26Seg<T>
Models & Types · AiDotNet.ComputerVision.Segmentation.InstanceSegmentation
YOLO26-Seg: Latest YOLO family instance segmentation with advanced CSP design.
Inheritance: NeuralNetworkBase<T> → SegmentationModelBase<T> → InstanceSegmentationBase<T> → YOLO26Seg<T>
For Beginners
State-of-the-art real-time segmentation. Production deployment on GPU and edge.
Common use cases:
- State-of-the-art real-time segmentation
- Production deployment on GPU and edge
- Video stream processing
- Multi-object tracking with masks
How It Works
Technical Details:
- Advanced Cross-Stage Partial design
- Improved feature pyramid network
- Anchor-free detection with mask prediction
- Optimized for TensorRT and ONNX export
Reference: Ultralytics, “YOLO26”, 2025.
Example
// Create a YOLO26-Seg model for state-of-the-art real-time segmentation
var architecture = new NeuralNetworkArchitecture<double>(
inputType: InputType.ThreeDimensional,
taskType: NeuralNetworkTaskType.MultiClassClassification,
inputHeight: 640, inputWidth: 640, inputDepth: 3, outputSize: 80);
var model = new YOLO26Seg<double>(architecture);
// Every tunable is now set through the options object; these are the defaults:
var custom = new YOLO26Seg<double>(architecture,
options: new YOLO26SegOptions { NumClasses = 80, DropRate = 0, ModelSize = YOLO26SegModelSize.N });
// Or load a pre-trained ONNX model optimized for TensorRT
var onnxModel = new YOLO26Seg<double>(architecture, "yolo26n-seg.onnx");
Constructors
| Constructor | Summary |
|---|---|
YOLO26Seg(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer, ILossFunction<T> lossFunction, YOLO26SegOptions options) |
Initializes YOLO26Seg in native (trainable) mode. |
YOLO26Seg(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, YOLO26SegOptions options) |
Initializes YOLO26Seg in ONNX (inference-only) mode. |
Methods
| Method | Summary |
|---|---|
InstanceSegmentationResult<T> DetectInstances(Tensor<T> image) |
|
ModelMetadata<T> GetModelMetadata() |
Collects metadata describing this model’s configuration. |