feat(ODEngine): load a model from memory, not only from a path

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>
This commit is contained in:
2026-09-12 20:29:59 +10:00
co-authored by Claude Opus 5
parent 430c8057b8
commit 5820a5e61b
13 changed files with 131 additions and 33 deletions
+3
View File
@@ -2,6 +2,7 @@
#define ANSONNXSEG_H
#pragma once
#include "ANSEngineCommon.h"
#include "ANSModelSource.h"
#include "engine.h"
namespace ANSCENTER {
@@ -50,6 +51,8 @@ namespace ANSCENTER {
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.