public class SegResult : DetResultExtends DetResult with additional segmentation mask capability. Used for dense prediction tasks where each pixel needs classification.
继承自DetResult并增加了分割掩码功能。 用于需要像素级分类的密集预测任务。
var segResult = new SegResult
{
Bounds = new Rect(100, 150, 200, 200),
Mask = new ImageDataF(width: 200, height: 200, channels: 1),
Confidence = 0.92f,
Category = "road"
};| SegResult | Initializes a new segmentation result with proper type configuration 初始化一个新的分割结果，自动配置正确的结果类型 |
| Bounds |
Bounding box coordinates relative to source image
相对于源图像的边界框坐标
(继承自 DetResult。) |
| Category |
Category/class name of the result
结果的类别/分类名称
(继承自 Result。) |
| Confidence |
Confidence score between 0 and 1
置信度分数(0到1之间)
(继承自 Result。) |
| Id |
Numeric identifier of the result
结果的数字标识符
(继承自 Result。) |
| ImageSize |
Size of the source input image
输入源图像的尺寸
(继承自 Result。) |
| Mask | Pixel-wise segmentation mask represented as floating-point image data 像素级分割掩码，表示为浮点型图像数据 |
| Type |
Type of the inference result
推理结果的类型
(继承自 Result。) |
| Clone | Creates a deep copy of this segmentation result 创建此分割结果的深拷贝 |
| Equals | Determines whether the specified object is equal to the current object. (继承自 Object。) |
| Finalize | Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection. (继承自 Object。) |
| GetHashCode | Serves as the default hash function. (继承自 Object。) |
| GetType | Gets the Type of the current instance. (继承自 Object。) |
| MemberwiseClone | Creates a shallow copy of the current Object. (继承自 Object。) |
| ToString |
Returns formatted string representation including mask dimensions
返回包含掩码尺寸的格式化字符串表示
(重写 DetResultToString) |
| UpdateCategory |
Updates the category from a categories array
从类别数组中更新类别
(继承自 Result。) |