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>
100 lines
5.4 KiB
C++
100 lines
5.4 KiB
C++
#ifndef ANSONNXCL_H
|
|
#define ANSONNXCL_H
|
|
#pragma once
|
|
#include "ANSEngineCommon.h"
|
|
#include "ANSModelSource.h"
|
|
#include "engine.h"
|
|
#include <memory>
|
|
|
|
namespace ANSCENTER {
|
|
// Forward declaration: avoid pulling ANSONNXYOLO.h into every consumer of
|
|
// ANSONNXCL.h. Definition is included in ANSONNXCL.cpp.
|
|
class ANSONNXYOLO;
|
|
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
// ANSONNXCL — verification facade over ANSONNXYOLO.
|
|
//
|
|
// ANSONNXYOLO already auto-detects classification models (single 2D
|
|
// output [B, nc]) and routes through its own classification postprocess.
|
|
// It also has the safe DML config (DisableMemPattern + ORT_SEQUENTIAL +
|
|
// EXTENDED) and the IsDmlFatalError catch-and-rebuild path.
|
|
//
|
|
// We delegate every public method here to an internal ANSONNXYOLO so we
|
|
// can A/B test whether ANSONNXCL's own session/postprocess code is the
|
|
// real cause of the AMD same-process DML races we saw with the custom
|
|
// helmet model. Public ABI is unchanged — external callers don't move.
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
class ANSENGINE_API ANSONNXCL :public ANSODBase {
|
|
public:
|
|
// Explicit non-copy/non-move (see ANSONNXYOLO for dllexport rationale).
|
|
ANSONNXCL(const ANSONNXCL&) = delete;
|
|
ANSONNXCL& operator=(const ANSONNXCL&) = delete;
|
|
ANSONNXCL(ANSONNXCL&&) = delete;
|
|
ANSONNXCL& operator=(ANSONNXCL&&) = delete;
|
|
ANSONNXCL() = default;
|
|
|
|
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();
|
|
~ANSONNXCL();
|
|
private:
|
|
// The wrapped engine. Lazy-initialised on first public call so we
|
|
// don't pay the cost (and pull in the dependency) for callers who
|
|
// never use this class.
|
|
std::unique_ptr<ANSONNXYOLO> _yoloDelegate;
|
|
private:
|
|
std::string _modelFilePath;
|
|
bool _modelLoadValid;
|
|
bool _fp16{ false };
|
|
|
|
// DML device-lost recovery: when DirectML fails fatally
|
|
// (HRESULT 887A0005 device-removed, 80004005 graph/command-recorder
|
|
// E_FAIL, etc. — see ANSCENTER::IsDmlFatalError) the Ort::Session
|
|
// is permanently broken. We detect once, recreate on CPU via
|
|
// Init(_modelFilePath, inputImageShape_, /*useGPU=*/false), and
|
|
// suppress further error-log flooding via this flag.
|
|
bool _dmlDeviceLost{ false };
|
|
size_t vectorProduct(const std::vector<int64_t>& vector);
|
|
bool preprocessImageToTensor(const cv::Mat& image, cv::Mat& outImage,
|
|
const cv::Size& targetShape,
|
|
const cv::Scalar& color = cv::Scalar(0, 0, 0),
|
|
bool scaleUp = true,
|
|
const std::string& strategy = "resize");
|
|
void warmupModel();
|
|
bool Init(const std::string& modelPath, const cv::Size& targetInputShape, bool useGPU = true);
|
|
// Same load, from a model already in memory (an opened package).
|
|
bool Init(const ModelSource& model, const cv::Size& targetInputShape, bool useGPU = true);
|
|
bool preprocess(const cv::Mat& image, float*& blob, std::vector<int64_t>& inputTensorShape);
|
|
// outputTensors is non-const because GetTensorMutableData() (the
|
|
// ORT API that doesn't hang on AMD DirectML) requires a non-const
|
|
// Ort::Value receiver. See comment at the GetTensorMutableData
|
|
// call site in postprocess() for the full rationale.
|
|
std::vector<Object> postprocess(std::vector<Ort::Value>& outputTensors, const std::string& camera_id);
|
|
std::vector<Object> classify(const cv::Mat& image, const std::string& camera_id);
|
|
|
|
private:
|
|
Ort::Env env_{ nullptr };
|
|
Ort::SessionOptions sessionOptions_{ nullptr };
|
|
Ort::Session session_{ nullptr };
|
|
|
|
bool isDynamicInputShape_{};
|
|
cv::Size inputImageShape_{};
|
|
|
|
std::vector<Ort::AllocatedStringPtr> inputNodeNameAllocatedStrings_{};
|
|
std::vector<const char*> inputNames_{};
|
|
std::vector<Ort::AllocatedStringPtr> outputNodeNameAllocatedStrings_{};
|
|
std::vector<const char*> outputNames_{};
|
|
|
|
size_t numInputNodes_{}, numOutputNodes_{};
|
|
int numClasses_{ 0 };
|
|
float m_imgWidth = 0;
|
|
float m_imgHeight = 0;
|
|
};
|
|
}
|
|
#endif
|
|
#pragma once
|