Skip to content

A toolbox for deep learning model deployment using C++ YoloX | YoloV7 | YoloV8 | Gan | OCR | MobileVit | Scrfd | MobileSAM | StableDiffusion

License

Notifications You must be signed in to change notification settings

TalkUHulk/ai.deploy.box

Repository files navigation

English | 简体中文

📌AiDB : A toolbox for deep learning model deployment using C++. Abstract mainstream deep learning inference frameworks into unified interfaces, including ONNXRUNTIME, MNN, NCNN, TNN, PaddleLite, and OpenVINO. Provide deployment demo for multiple scenarios and languages. This project is not only used to record learning, but also a summary of my work over the past few years. If this project inspires you or helps you, welcome ⭐Star⭐ to support me, which is the driving force for me to keep updating! 🍔

📌Article

AiDB:一个集合了6大推理框架的AI工具箱 | 加速你的模型部署

知乎 | GiantPandaCV

如何使用“LoRa”的方式加载ONNX模型:StableDiffusion相关模型 的C++推理

知乎 | GiantPandaCV



wasm_capture.mp4
wasm_webcam.mp4

Features 🍉🍉

  • rich backend: integrating mainstream AI inference frameworks, including OnnxRuntime, MNN, NCNN, TNN, PaddleLite, and OpenVINO;
  • user friendly: abstracting all inference frameworks into a unified interface and selecting them through configuration files for ease of use;
  • multiple scenarios: support Linux、MacOS、Android(Win64 coming soon、IOS--poverty has limited my work),provide PC Demo(Qt)Android Demo(Kotlin)Lua Demo and minimal server deployment demo( Go Zeros and Python FastAPI )
  • multiple languages: provide calling instances for Python, Lua, and Go;

Demo 🍓🍓

  • Try out the web demo: Webassembly Demo

  • Run the C++ demo on Google Colab: Open In Colab

  • Run the Python demo on Google Colab: Open In Colab

  • Run the Go demo on Google Colab: Open In Colab

  • Run the Lua demo on Google Colab: Open In Colab

Demo Repo 🍇🍇

Contents 📖💡

FrameWork 📝 📝

There are two modes available, S mode(C api) and H mode(C++ api)

Quick Start ⚡⚡

environment

Recommend using Docker
docker pull mister5ive/ai.deploy.box

Build

Docker(recommend)

git lfs clone https://github.com/TalkUHulk/ai.deploy.box.git
cd ai.deploy.box.git
docker build -t aidb-dev .
docker run -it --name aidb-test aidb-dev

Build from source code

git lfs clone https://github.com/TalkUHulk/ai.deploy.box.git
cd ai.deploy.box.git
mkdir build && cd build
cmake .. -DC_API={ON/OFF} -DBUILD_SAMPLE={ON/OFF} -DBUILD_PYTHON={ON/OFF} -DBUILD_LUA={ON/OFF} -DENGINE_NCNN_WASM={ON/OFF} -DOPENCV_HAS_FREETYPE={ON/OFF} -DENGINE_MNN={ON/OFF} -DENGINE_ORT={ON/OFF} -DENGINE_NCNN={ON/OFF} -DENGINE_TNN={ON/OFF} -DENGINE_OPV={ON/OFF} -DENGINE_PPLite={ON/OFF}
make -j8
  • C_API: compile C library;
  • BUILD_PYTHON: compile Python api;
  • BUILD_LUA: compile Lua api;
  • OPENCV_HAS_FREETYPE: opencv-contrib complied with freetype or not. cv::putText can put chinese;
  • BUILD_SAMPLE: compile sample;
  • ENGINE_NCNN_WASM: compile sample;
  • ENGINE_MNN: enable mnn;
  • ENGINE_ORT: enable onnxruntim;
  • ENGINE_NCNN: enable ncnn;
  • ENGINE_TNN: enable tnn;
  • ENGINE_OPV: enable openvino;
  • ENGINE_PPLite: enable paddle-lite;
  • ENABLE_SD: enable stable diffusion;

Models

Model Lite: MEGA | Baidu: 92e8

[News!!!] All models convert to 🤗.

Model List
Demo Model name Model Type Pretrained From ONNX MNN NCNN OpenVINO TNN Paddle Lite

SCRFD_10G_WITH_KPS Face Detection insightface MEGA & Baidu[prv3] MEGA & Baidu[2sew] MEGA & Baidu[tpxe] MEGA & Baidu[m4u5] MEGA & Baidu[7ch9] MEGA & Baidu[75u6]

SCRFD_2.5G_WITH_KPS Face Detection insightface MEGA & Baidu[prv3] MEGA & Baidu[2sew] MEGA & Baidu[tpxe] MEGA & Baidu[m4u5] MEGA & Baidu[7ch9] MEGA & Baidu[75u6]
⬆️ SCRFD_500M_WITH_KPS Face Detection insightface MEGA & Baidu[prv3] MEGA & Baidu[2sew] MEGA & Baidu[tpxe] MEGA & Baidu[m4u5] MEGA & Baidu[7ch9] MEGA & Baidu[75u6]

PFPLD Face Landmark nniefacelib MEGA & Baidu[kufx] MEGA & Baidu[eciw] MEGA & Baidu[59jw] MEGA & Baidu[w6e7] MEGA & Baidu[d8qh] MEGA & Baidu[xeni]

BISENET Face Parsing face-parsing.PyTorch MEGA & Baidu[7hqw] MEGA & Baidu[rm5b] MEGA & Baidu[wx59] MEGA & Baidu[mcdi] MEGA & Baidu[vwj9] MEGA & Baidu[xzwk]

3DDFAV2_MB1_BASE Face Alignment 3DDFA_V2 MEGA & Baidu[ccei] MEGA & Baidu[nrrx] MEGA & Baidu[mqps] MEGA & Baidu[ydtb] MEGA & Baidu[rrgv] MEGA & Baidu[fkvc]

3DDFAV2_MB1_DENSE Face Alignment 3DDFA_V2 MEGA & Baidu[ccei] MEGA & Baidu[nrrx] MEGA & Baidu[mqps] MEGA & Baidu[ydtb] MEGA & Baidu[rrgv] MEGA & Baidu[fkvc]

3DDFAV2_MB05_BASE Face Alignment 3DDFA_V2 MEGA & Baidu[ccei] MEGA & Baidu[nrrx] MEGA & Baidu[mqps] MEGA & Baidu[ydtb] MEGA & Baidu[rrgv] MEGA & Baidu[fkvc]

3DDFAV2_MB05_DENSE Face Alignment 3DDFA_V2 MEGA & Baidu[ccei] MEGA & Baidu[nrrx] MEGA & Baidu[mqps] MEGA & Baidu[ydtb] MEGA & Baidu[rrgv] MEGA & Baidu[fkvc]

YOLOX_TINY Object Detection YOLOX MEGA & Baidu[vuwe] MEGA & Baidu[xf8g] MEGA & Baidu[tix9] MEGA & Baidu[3eij] MEGA & Baidu[4n7z] MEGA & Baidu[vd8x]

YOLOX_NANO Object Detection YOLOX MEGA & Baidu[vuwe] MEGA & Baidu[xf8g] MEGA & Baidu[tix9] MEGA & Baidu[3eij] MEGA & Baidu[4n7z] MEGA & Baidu[vd8x]
⬆️ YOLOX_S Object Detection YOLOX MEGA & Baidu[vuwe] MEGA & Baidu[xf8g] MEGA & Baidu[tix9] MEGA & Baidu[3eij] MEGA & Baidu[4n7z] MEGA & Baidu[vd8x]
⬆️ YOLOX_M Object Detection YOLOX MEGA & Baidu[vuwe] MEGA & Baidu[xf8g] MEGA & Baidu[tix9] MEGA & Baidu[3eij] MEGA & Baidu[4n7z] MEGA & Baidu[vd8x]
⬆️ YOLOX_L Object Detection YOLOX MEGA & Baidu[vuwe] MEGA & Baidu[xf8g] MEGA & Baidu[tix9] MEGA & Baidu[3eij] MEGA & Baidu[4n7z] MEGA & Baidu[vd8x]
⬆️ YOLOX_X Object Detection YOLOX MEGA & Baidu[vuwe] MEGA & Baidu[xf8g] MEGA & Baidu[tix9] MEGA & Baidu[3eij] MEGA & Baidu[4n7z] MEGA & Baidu[vd8x]
⬆️ YOLOX_DARKNET Object Detection YOLOX MEGA & Baidu[vuwe] MEGA & Baidu[xf8g] MEGA & Baidu[tix9] MEGA & Baidu[3eij] MEGA & Baidu[4n7z] MEGA & Baidu[vd8x]

YOLOV7_TINY Object Detection yolov7 MEGA & Baidu[uax8] MEGA & Baidu[s7qm] MEGA & Baidu[nzun] MEGA & Baidu[4dmi] MEGA & Baidu[5y8d] MEGA & Baidu[c5d5]

YOLOV7_TINY_GRID Object Detection yolov7 MEGA & Baidu[uax8] MEGA & Baidu[s7qm] MEGA & Baidu[4dmi] MEGA & Baidu[5y8d] MEGA & Baidu[c5d5]
⬆️ YOLOV7 Object Detection yolov7 MEGA & Baidu[uax8] MEGA & Baidu[s7qm] MEGA & Baidu[nzun] MEGA & Baidu[4dmi] MEGA & Baidu[5y8d] MEGA & Baidu[c5d5]
⬆️ YOLOV7_GRID Object Detection yolov7 MEGA & Baidu[uax8] MEGA & Baidu[s7qm] MEGA & Baidu[4dmi] MEGA & Baidu[5y8d] MEGA & Baidu[c5d5]
⬆️ YOLOV7X Object Detection yolov7 MEGA & Baidu[uax8] MEGA & Baidu[s7qm] MEGA & Baidu[nzun] MEGA & Baidu[4dmi] MEGA & Baidu[5y8d] MEGA & Baidu[c5d5]
⬆️ YOLOV7X_GRID Object Detection yolov7 MEGA & Baidu[uax8] MEGA & Baidu[s7qm] MEGA & Baidu[4dmi] MEGA & Baidu[5y8d] MEGA & Baidu[c5d5]
⬆️ YOLOV7_D6_GRID Object Detection yolov7 MEGA & Baidu[uax8] MEGA & Baidu[s7qm] MEGA & Baidu[4dmi] MEGA & Baidu[5y8d] MEGA & Baidu[c5d5]
⬆️ YOLOV7_E6_GRID Object Detection yolov7 MEGA & Baidu[uax8] MEGA & Baidu[s7qm] MEGA & Baidu[4dmi] MEGA & Baidu[5y8d] MEGA & Baidu[c5d5]

YOLOV8_N Object Detection ultralytics MEGA & Baidu[ztvu] MEGA & Baidu[bwx7] MEGA & Baidu[ihu9] MEGA & Baidu[z5mq] MEGA & Baidu[qy7k] MEGA & Baidu[qb2a]

YOLOV8_S Object Detection ultralytics MEGA & Baidu[ztvu] MEGA & Baidu[bwx7] MEGA & Baidu[ihu9] MEGA & Baidu[z5mq] MEGA & Baidu[qy7k] MEGA & Baidu[qb2a]
⬆️ YOLOV8_M Object Detection ultralytics MEGA & Baidu[ztvu] MEGA & Baidu[bwx7] MEGA & Baidu[ihu9] MEGA & Baidu[z5mq] MEGA & Baidu[qy7k] MEGA & Baidu[qb2a]
⬆️ YOLOV8_L Object Detection ultralytics MEGA & Baidu[ztvu] MEGA & Baidu[bwx7] MEGA & Baidu[ihu9] MEGA & Baidu[z5mq] MEGA & Baidu[qy7k] MEGA & Baidu[qb2a]
⬆️ YOLOV8_X Object Detection ultralytics MEGA & Baidu[ztvu] MEGA & Baidu[bwx7] MEGA & Baidu[ihu9] MEGA & Baidu[z5mq] MEGA & Baidu[qy7k] MEGA & Baidu[qb2a]

MOVENET KeyPoints Detection movenet.pytorch MEGA & Baidu[q5i8] MEGA & Baidu[fpia] MEGA & Baidu[yhdp] MEGA & Baidu[43hb] MEGA & Baidu[m73t] MEGA & Baidu[h7th]

PADDLE_OCR OCR PaddleOCR MEGA & Baidu[m1ru] MEGA & Baidu[a3hb] MEGA & Baidu[pri5] MEGA & Baidu[81nm] MEGA & Baidu[qkc9]
🈚️ MOBILE_VIT_S Classification MobileViT MEGA & Baidu[mgpn] MEGA & Baidu[576h] MEGA & Baidu[6nkb]
🈚️ MOBILE_VIT_XXS Classification MobileViT MEGA & Baidu[mgpn] MEGA & Baidu[576h] MEGA & Baidu[6nkb]

ANIME_PAPRIKA Gan AnimeGANv2 MEGA & Baidu[2xa6] MEGA & Baidu[niqg] MEGA & Baidu[q8uv]
⬆️ ANIME_PAPRIKA_DYN Gan AnimeGANv2 MEGA & Baidu[2xa6] MEGA & Baidu[niqg] MEGA & Baidu[q8uv]

ANIME_FACEPAINT_V1 Gan AnimeGANv2 MEGA & Baidu[2xa6] MEGA & Baidu[niqg] MEGA & Baidu[q8uv]
⬆️ ANIME_FACEPAINT_V1_DYN Gan AnimeGANv2 MEGA & Baidu[2xa6] MEGA & Baidu[niqg] MEGA & Baidu[q8uv]

ANIME_FACEPAINT_V2 Gan AnimeGANv2 MEGA & Baidu[2xa6] MEGA & Baidu[niqg] MEGA & Baidu[q8uv]
⬆️ ANIME_FACEPAINT_V2_DYN Gan AnimeGANv2 MEGA & Baidu[2xa6] MEGA & Baidu[niqg] MEGA & Baidu[q8uv]

ANIME_CELEBA Gan AnimeGANv2 MEGA & Baidu[2xa6] MEGA & Baidu[niqg] MEGA & Baidu[q8uv]
⬆️ ANIME_CELEBA_DYN Gan AnimeGANv2 MEGA & Baidu[2xa6] MEGA & Baidu[niqg] MEGA & Baidu[q8uv]

MOBILE_STYLEGAN Gan MobileStyleGAN.pytorch MEGA & Baidu[d5dk] MEGA & Baidu[tcic] MEGA & Baidu[n79w]

MOBILE_SAM SAM MobileSAM MEGA & Baidu[waxt] MEGA & Baidu[77rn] MEGA & Baidu[yrph]

MOBILE_SAM SAM MobileSAM MEGA & Baidu[waxt] MEGA & Baidu[77rn] MEGA & Baidu[yrph]

ThinPlateSplineMotionModel Thin-Plate-Spline-Motion-Model MEGA & Baidu[fcxw] MEGA & Baidu[eh3w] MEGA & Baidu[sdkv]

StableDiffusionInpainting StableDiffusion stable-diffusion-inpainting huggingface

StableDiffusionControlNetImg2Img StableDiffusion ControlNet huggingface

Usage

Example: use scrfd detect face by mnn:

#include <opencv2/opencv.hpp>
#include "Interpreter.h"
#include "utility/Utility.h"

auto interpreter = AIDB::Interpreter::createInstance("scrfd_500m_kps", "mnn");

auto bgr = cv::imread("./doc/test/face.jpg");

cv::Mat blob = *det_ins << bgr;

std::vector<std::vector<float>> outputs;

std::vector<std::vector<int>> outputs_shape;

det_ins->forward((float*)blob.data, det_ins->width(), det_ins->height(), det_ins->channel(), outputs, outputs_shape);

std::vector<std::shared_ptr<AIDB::FaceMeta>> face_metas;

assert(face_detect_input->scale_h() == face_detect_input->scale_w());

AIDB::Utility::scrfd_post_process(outputs, face_metas, det_ins->width(), det_ins->height(), det_ins->scale_h());

Sample Usage

In linux, run source set_env.sh before test.

Sample Usage

Face Detect

Face Detect
./build/samples/FaceDetect model_name backend type inputfile
  • model_name

    • scrfd_10g_kps
    • scrfd_2.5g_kps
    • scrfd_500m_kps
  • backend

    • ONNX
    • MNN
    • NCNN
    • OpenVINO
    • TNN
    • PaddleLite
  • type

    • 0 - image
    • 1 - video
  • inputfile: 0 is webcam

Face Landmark

Face landmark
./build/samples/FaceDetectWithLandmark model_name backend pfpld backend type inputfile
  • model_name

    • scrfd_10g_kps
    • scrfd_2.5g_kps
    • scrfd_500m_kps
  • backend

    • ONNX
    • MNN
    • NCNN
    • OpenVINO
    • TNN
    • PaddleLite
  • type

    • 0 - image
    • 1 - video
  • inputfile: 0 is webcam

Face Alignment

Face Alignment
./build/samples/FaceDetectWith3DDFA det_model_name backend tddfa_model_name backend type inputfile
  • det_backend

    • scrfd_10g_kps
    • scrfd_2.5g_kps
    • scrfd_500m_kps
  • tddfa_model_name

    • 3ddfa_mb1_bfm_base
    • 3ddfa_mb1_bfm_dense
    • 3ddfa_mb05_bfm_base
    • 3ddfa_mb05_bfm_dense
  • backend

    • ONNX
    • MNN
    • NCNN
    • OpenVINO
    • TNN
    • PaddleLite
  • type

    • 0 - image
    • 1 - video
  • inputfile: 0 is webcam

Face Parsing

Face Parsing
./build/samples/FaceParsing bisenet backend type inputfile
  • backend

    • ONNX
    • MNN
    • NCNN
    • OpenVINO
    • TNN
    • PaddleLite
  • type

    • 0 - image
    • 1 - video
  • inputfile: 0 is webcam

OCR

Ocr
./build/samples/PPOcr ppocr_det det_backend ppocr_cls cls_backend ppocr_ret rec_backend  type inputfile
  • det_backend/cls_backend/rec_backend

    • ONNX
    • MNN
    • NCNN
    • OpenVINO
    • PaddleLite
  • type

    • 0 - image
    • 1 - video
  • inputfile: 0 is webcam

YoloX

YoloX
./build/samples/YoloX model_name backend type inputfile
  • model_name

    • yolox_tiny
    • yolox_nano
    • yolox_s
    • yolox_m
    • yolox_l
    • yolox_x
    • yolox_darknet
  • backend

    • ONNX
    • MNN
    • NCNN
    • OpenVINO
    • TNN
    • PaddleLite
  • type

    • 0 - image
    • 1 - video
  • inputfile: 0 is webcam

YoloV7

YoloV7
./build/samples/YoloV7 model_name backend type inputfile
  • model_name

    • yolov7_tiny
    • yolov7_tiny_grid
    • yolov7
    • yolov7_grid
    • yolov7x
    • yolov7x_grid
    • yolov7_d6_grid
    • yolov7_e6_grid
  • backend

    • ONNX
    • MNN
    • NCNN
    • OpenVINO
    • TNN
    • PaddleLite
  • type

    • 0 - image
    • 1 - video
  • inputfile: 0 is webcam

YoloV8

YoloV8
./build/samples/YoloV8 model_name backend type inputfile
  • model_name

    • yolov8n
    • yolov8s
    • yolov8m
    • yolov8l
    • yolov8x
  • backend

    • ONNX
    • MNN
    • NCNN
    • OpenVINO
    • TNN
    • PaddleLite
  • type

    • 0 - image
    • 1 - video
  • inputfile: 0 is webcam

MobileVit

MobileVit
./build/samples/MobileViT model_name backend inputfile
  • model_name

    • mobilevit_xxs
    • mobilevit_s
  • backend

    • ONNX
    • MNN
    • OpenVINO

MoveNet

MoveNet
./build/samples/Movenet movenet backend type inputfile
  • backend

    • ONNX
    • MNN
    • NCNN
    • OpenVINO
    • TNN
    • PaddleLite
  • type

    • 0 - image
    • 1 - video
  • inputfile: 0 is webcam

MobileStyleGan

MobileStyleGan
./build/samples/MobileStyleGan mobilestylegan_mappingnetwork map_backend mobilestylegan_synthesisnetwork syn_backend
  • map_backend/syn_backend
    • ONNX
    • MNN
    • OpenVINO

AnimeGan

AnimeGan
./build/samples/AnimeGan model_name backend 0 inputfile
  • model_name

    • animeganv2_celeba_distill
    • animeganv2_celeba_distill_dynamic
    • animeganv2_face_paint_v1
    • animeganv2_face_paint_v1_dynamic
    • animeganv2_face_paint_v2
    • animeganv2_face_paint_v2_dynamic
    • animeganv2_paprika
    • animeganv2_paprika_dynamic
  • backend

    • ONNX
    • MNN
    • OpenVINO

Pitfalls 🐱 🐶 🐭 🐹 🐰 🐺 🐸 🐯 🐨 🐻 🐷

Pitfalls
  1. Android-rtti

Q:

XXXX/3rdparty/yaml-cpp/depthguard.h:54:9: error: cannot use 'throw' with exceptions disabled

In file included from XXXX/opencv/native/jni/include/opencv2/opencv.hpp:65:
In file included from XXXX/opencv/native/jni/include/opencv2/flann.hpp:48:
In file included from XXXX/opencv/native/jni/include/opencv2/flann/flann_base.hpp:41:
In file included from XXXX/opencv/native/jni/include/opencv2/flann/params.h:35:
XXXX/opencv/native/jni/include/opencv2/flann/any.h:60:63: error: use of typeid requires -frtti

A: app->build.gradle add "-fexceptions"

externalNativeBuild {
            ndkBuild {
                cppFlags "-std=c++11", "-fexceptions"
                arguments  "APP_OPTIM=release", "NDK_DEBUG=0"
                abiFilters "arm64-v8a"
            }
        }

if complie with ncnn, disable rtti.

cmake -DCMAKE_TOOLCHAIN_FILE=../../android-ndk-r25c/build/cmake/android.toolchain.cmake -DANDROID_ABI="arm64-v8a"  -DANDROID_PLATFORM=android-24 -DNCNN_SHARED_LIB=ON  -DANDROID_ARM_NEON=ON -DNCNN_DISABLE_EXCEPTION=OFF -DNCNN_DISABLE_RTTI=OFF ..

reference: issues/3231

  1. Android-mnn

Q:

I/MNNJNI: Can't Find type=3 backend, use 0 instead 

A:

java load so 时,显式调 System.load("libMNN_CL.so") 。在 CMakeLists.txt 里面让你的 so link libMNN_CL 貌似是不行的。
init {
            System.loadLibrary("aidb")
            System.loadLibrary("MNN");
            try {
                System.loadLibrary("MNN_CL")
                System.loadLibrary("MNN_Express")
                System.loadLibrary("MNN_Vulkan")
            } catch (ce: Throwable) {
                Log.w("MNNJNI", "load MNN GPU so exception=%s", ce)
            }
            System.loadLibrary("mnncore")
}
  1. Android Studio

Q:

Out of memory:Java heap space

A:

gradle.properties->org.gradle.jvmargs=-Xmx4g -Dfile.encoding=UTF-8
  1. Android paddle-lite

Q: because kernel for 'calib' is not supported by Paddle-Lite. A: 使用带fp16标签的库

Q: kernel for 'conv2d' is not supported by Paddle-lite. A: 转模型--valid_targets =arm, 打开fp16,opt\lib版本对应

  1. Android OpenVINO

Q: How to deploy models in android with openvino(reference).

A:

  • step1

    • build openvino library. Here are my compilation instructions:
      cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_TOOLCHAIN_FILE=android-ndk-r25c/build/cmake/android.toolchain.cmake -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=30 -DANDROID_STL=c++_shared  -DENABLE_SAMPLES=OFF  -DENABLE_OPENCV=OFF -DENABLE_CLDNN=OFF -DENABLE_VPU=OFF  -DENABLE_GNA=OFF -DENABLE_MYRIAD=OFF -DENABLE_TESTS=OFF  -DENABLE_GAPI_TESTS=OFF  -DENABLE_BEH_TESTS=OFF ..
  • step2

    • Put openvino library(*.so) to assets.(plugin you need)
  • step3

    • If your device is not root, put libc++.so and libc++_shared.so to assets.

Q:

dlopen failed: library “libc++_shared.so“ not found

A:

cmakelist.txt

add_library(libc++_shared STATIC IMPORTED)
set_target_properties(libc++_shared PROPERTIES IMPORTED_LOCATION ${CMAKE_CURRENT_LIST_DIR}/../libs/android/opencv/native/libs/${ANDROID_ABI}/libc++_shared.so)

Q:

java.lang.UnsatisfiedLinkError: dlopen failed: cannot locate symbol "__emutls_get_address" referenced by "https://accionvegana.org/accio/0ITbvNmLiVHa0l2Z6MHc0/data/app/~~DMBfRqeqFvKzb9yUIkUZiQ==/com.hulk.aidb_demo-HrziaiyGs2adLTT-aQqemg==/lib/arm64/libopenvino_arm_cpu_plugin.so"...

A: Build openvino arm library, and put *.so in app/libs/${ANDROID_ABI}/. (need add jniLibs.srcDirs = ['libs'] in build.gradle)

Q:

library "https://accionvegana.org/accio/0ITbvNmLiVHa0l2Z6MHc0/system/lib64/libc++.so" ("https://accionvegana.org/accio/0ITbvNmLiVHa0l2Z6MHc0/system/lib64/libc++.so") needed or dlopened by "https://accionvegana.org/accio/0ITbvNmLiVHa0l2Z6MHc0/apex/com.android.art/lib64/libnativeloader.so" is not accessible for the namespace: [name="classloader-namespace", ld_library_paths="", default_library_paths="https://accionvegana.org/accio/0ITbvNmLiVHa0l2Z6MHc0/data/app/~~IWBQrjWXHt7o71mstUGRHA==/com.hulk.aidb_demo-cfq3aSk8DN62UDtoKV4Vfg==/lib/arm64:/data/app/~~IWBQrjWXHt7o71mstUGRHA==/com.hulk.aidb_demo-cfq3aSk8DN62UDtoKV4Vfg==/base.apk!/lib/arm64-v8a", permitted_paths="https://accionvegana.org/accio/0ITbvNmLiVHa0l2Z6MHc0/data:/mnt/expand:/data/data/com.hulk.aidb_demo"]

A: Put libc++.so in android studio app/libs/${ANDROID_ABI}/. (need add jniLibs.srcDirs = ['libs'] in build.gradle)

Maintainers

@TalkUHulk.

Contributing

Feel free to dive in! Open an issue or submit PRs.

AiDB follows the Contributor Covenant Code of Conduct.

Contributors

This project exists thanks to all the people who contribute.

License

MIT © Hulk Wang