Every engine built its session from a file path, which is why opening an encrypted model package means inflating it to a directory first: the unprotected model lands on disk, is optimised, and is zipped back into a cache. The new package format cannot avoid that from the outside — the engines have to be able to take bytes. ANSModelSource.h introduces a ModelSource (a path, or bytes with a name for logs) and one MakeSession that builds from either. The six ONNX engines — classification, OBB, pose, segmentation, YOLO12 and YOLO — each gain a load overload taking it, with the existing string form delegating so no caller changes. The Windows wide-path conversion and the from-memory call now live in one place instead of the eleven copies they were spread across; YOLOOD, which had only the Windows branch, becomes portable as a side effect. The factories are named rather than implicit, so a call with a plain string literal still resolves to the path overload without ambiguity. Not compiled here: this layer builds only where CUDA is present, so verification on this machine was the new header compiled and run, plus a structural check that every engine declares and defines both overloads, calls MakeSession exactly once, and has no raw session construction left. It needs a build on a CUDA box before it ships. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
90 lines
4.5 KiB
C++
90 lines
4.5 KiB
C++
#ifndef ANSONNXSEG_H
|
|
#define ANSONNXSEG_H
|
|
#pragma once
|
|
#include "ANSEngineCommon.h"
|
|
#include "ANSModelSource.h"
|
|
#include "engine.h"
|
|
|
|
namespace ANSCENTER {
|
|
class ANSENGINE_API ANSONNXSEG :public ANSODBase {
|
|
public:
|
|
virtual bool Initialize(std::string licenseKey, ModelConfig modelConfig, const std::string& modelZipFilePath, const std::string& modelZipPassword, std::string& labelMap) override;
|
|
virtual bool LoadModel(const std::string& modelZipFilePath, const std::string& modelZipPassword)override;
|
|
virtual bool LoadModelFromFolder(std::string licenseKey, ModelConfig modelConfig, std::string modelName, std::string className, const std::string& modelFolder, std::string& labelMap)override;
|
|
virtual bool OptimizeModel(bool fp16, std::string& optimizedModelFolder);
|
|
std::vector<Object> RunInference(const cv::Mat& input);
|
|
std::vector<Object> RunInference(const cv::Mat& input, const std::string& camera_id);
|
|
bool Destroy();
|
|
~ANSONNXSEG();
|
|
int getInstanceId() const { return instanceId_; }
|
|
private:
|
|
std::string _modelFilePath;
|
|
bool _modelLoadValid;
|
|
bool _fp16{ false };
|
|
size_t vectorProduct(const std::vector<int64_t>& vector);
|
|
void letterBox(const cv::Mat& image,
|
|
cv::Mat& outImage,
|
|
const cv::Size& newShape,
|
|
const cv::Scalar& color = cv::Scalar(114, 114, 114),
|
|
bool auto_ = true,
|
|
bool scaleFill = false,
|
|
bool scaleUp = true,
|
|
int stride = 32);
|
|
BoundingBox scaleCoords(const cv::Size& letterboxShape,
|
|
const BoundingBox& coords,
|
|
const cv::Size& originalShape,
|
|
bool p_Clip = true);
|
|
std::vector<cv::Scalar> generateColors(const std::vector<std::string>& classNames, int seed = 42);
|
|
cv::Mat sigmoid(const cv::Mat& src);
|
|
void NMSBoxes(const std::vector<BoundingBox>& boxes,
|
|
const std::vector<float>& scores,
|
|
float scoreThreshold,
|
|
float nmsThreshold,
|
|
std::vector<int>& indices);
|
|
void drawSegmentations(cv::Mat& image,
|
|
const std::vector<Object>& results,
|
|
float maskAlpha = 0.5f) const;
|
|
void drawSegmentationsAndBoxes(cv::Mat& image,
|
|
const std::vector<Object>& results,
|
|
float maskAlpha) const;
|
|
const std::vector<cv::Scalar>& getClassColors() const { return classColors; }
|
|
|
|
void warmupModel();
|
|
bool Init(const std::string& modelPath, bool useGPU=true, int deviceId = 0);
|
|
// Same load, from a model already in memory (an opened package).
|
|
bool Init(const ModelSource& model, bool useGPU = true, int deviceId = 0);
|
|
cv::Mat preprocess(const cv::Mat& image,float*& blobPtr,std::vector<int64_t>& inputTensorShape);
|
|
// outputs is non-const because GetTensorMutableData() requires a
|
|
// non-const Ort::Value receiver — see ANSONNXCL.h for full note.
|
|
std::vector<Object> postprocess(const cv::Size& origSize,const cv::Size& letterboxSize,
|
|
std::vector<Ort::Value>& outputs, const std::string& camera_id);
|
|
std::vector<Object> segment(const cv::Mat& image, const std::string& camera_id);
|
|
std::vector<cv::Point2f> maskToPolygon(const cv::Mat& binaryMask,
|
|
const cv::Rect& boundingBox,
|
|
float simplificationEpsilon = 2.0f,
|
|
int minContourArea = 10);
|
|
private:
|
|
static std::atomic<int> instanceCounter_; // Thread-safe counter
|
|
int instanceId_;
|
|
int deviceId_ = 0;
|
|
Ort::Env env{ nullptr }; // ONNX Runtime environment
|
|
Ort::SessionOptions sessionOptions{ nullptr }; // Session options for ONNX Runtime
|
|
Ort::Session session{ nullptr }; // ONNX Runtime session for running inference
|
|
bool isDynamicInputShape{}; // Flag indicating if input shape is dynamic
|
|
cv::Size inputImageShape; // Expected input image shape for the model
|
|
|
|
// Vectors to hold allocated input and output node names
|
|
std::vector<Ort::AllocatedStringPtr> inputNameAllocs;
|
|
std::vector<const char*> inputNames;
|
|
std::vector<Ort::AllocatedStringPtr> outputNameAllocs;
|
|
std::vector<const char*> outputNames;
|
|
size_t numInputNodes, numOutputNodes; // Number of input and output nodes in the model
|
|
std::vector<cv::Scalar> classColors;
|
|
|
|
float m_imgWidth = 0;
|
|
float m_imgHeight = 0;
|
|
};
|
|
}
|
|
#endif
|
|
#pragma once
|