【MNN學習一】基於Linux的MNN編譯安裝，模型轉換以及benchmark測試

原創 @Vivia 2019-09-02 22:08

目錄

一. MNN編譯安裝 (MNN編譯)

二. 編譯模型轉換工具MNNConvert (MNNConvert)

三. 下載模型並使用MNNConvert (模型下載&轉換)

四. 測試benchmark

一. MNN編譯安裝 (MNN編譯)

1. 編譯選項

cmake_minimum_required(VERSION 2.8)

project(MNN)

# complier options
set(CMAKE_C_STANDARD 99)
set(CMAKE_CXX_STANDARD 11)
enable_language(ASM)
# set(CMAKE_C_COMPILER gcc)
# set(CMAKE_CXX_COMPILER g++)

option(MNN_USE_CPP11 "Enable MNN use c++11" ON)

if (NOT MSVC)
    if(MNN_USE_CPP11)
        set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=gnu99")
        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
    else()
        set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=gnu99")
        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++0x")
    endif()
endif()

# build options
option(MNN_BUILD_HARD "Build -mfloat-abi=hard or not" OFF)
option(MNN_BUILD_SHARED_LIBS "MNN build shared or static lib" ON)
option(MNN_FORBID_MULTI_THREAD "Disable Multi Thread" OFF)
option(MNN_OPENMP "Enable Multiple Thread Linux|Android" ON)
option(MNN_USE_THREAD_POOL "Use Multiple Thread by Self ThreadPool" OFF)
option(MNN_SUPPORT_TRAIN "Enable Train Ops" ON)
option(MNN_BUILD_DEMO "Build demo/exec or not" ON)
option(MNN_BUILD_QUANTOOLS "Build Quantized Tools or not" ON)
option(MNN_USE_INT8_FAST "Build int8 or not" ON)

if (MNN_USE_THREAD_POOL)
    set(MNN_OPENMP OFF)
    add_definitions(-DMNN_USE_THREAD_POOL)
endif()

if(MNN_FORBID_MULTI_THREAD)
    add_definitions(-DMNN_FORBIT_MULTI_THREADS)
endif()
if(MNN_USE_INT8_FAST)
    add_definitions(-DMNN_USE_INT8_FAST)
endif()

# debug options
option(MNN_DEBUG "Enable MNN DEBUG" OFF)
if(CMAKE_BUILD_TYPE MATCHES "Debug")
    set(MNN_DEBUG ON)
endif()
option(MNN_DEBUG_MEMORY "MNN Debug Memory Access" OFF)
option(MNN_DEBUG_TENSOR_SIZE "Enable Tensor Size" OFF )
option(MNN_GPU_TRACE "Enable MNN Gpu Debug" OFF)

if(MNN_DEBUG_MEMORY)
    add_definitions(-DMNN_DEBUG_MEMORY)
endif()
if(MNN_DEBUG_TENSOR_SIZE)
    add_definitions(-DMNN_DEBUG_TENSOR_SIZE)
endif()
if(MNN_GPU_TRACE)
    add_definitions(-DMNN_GPU_FORCE_FINISH)
endif()

# backend options
option(MNN_METAL "Enable Metal" OFF)
option(MNN_OPENCL "Enable OpenCL" ON)
option(MNN_OPENGL "Enable OpenGL" OFF)
option(MNN_VULKAN "Enable Vulkan" OFF)
option(MNN_ARM82 "Enable ARM82" ON)

# codegen register ops
if (MNN_METAL)
    add_definitions(-DMNN_CODEGEN_REGISTER)
endif()

# target options
option(MNN_BUILD_BENCHMARK "Build benchmark or not" ON)
option(MNN_BUILD_TEST "Build tests or not" ON)
option(MNN_BUILD_FOR_ANDROID_COMMAND "Build from command" OFF)
option(MNN_BUILD_FOR_IOS "Build for ios" OFF)
set (MNN_HIDDEN FALSE)
if (NOT MNN_BUILD_TEST)
    if (NOT MNN_DEBUG)
        set (MNN_HIDDEN TRUE)
    endif()
endif()

include(cmake/macros.cmake)

message(STATUS ">>>>>>>>>>>>>")
message(STATUS "MNN BUILD INFO:")
message(STATUS "\tSystem: ${CMAKE_SYSTEM_NAME}")
message(STATUS "\tProcessor: ${CMAKE_SYSTEM_PROCESSOR}")
message(STATUS "\tDEBUG: ${MNN_DEBUG}")
message(STATUS "\tMetal: ${MNN_METAL}")
message(STATUS "\tOpenCL: ${MNN_OPENCL}")
message(STATUS "\tOpenGL: ${MNN_OPENGL}")
message(STATUS "\tVulkan: ${MNN_VULKAN}")
message(STATUS "\tOpenMP: ${MNN_OPENMP}")
message(STATUS "\tHideen: ${MNN_HIDDEN}")

.
.
.
.

2. 本地編譯

    在這一步中先忽略第四小步，在MNNConvert安裝以後再./tools/script/get_model.sh

二. 編譯模型轉換工具MNNConvert (MNNConvert)

1. 安裝protobuf(3.0以上) (Protocol Buffers - Google's data interchange format)

sudo apt-get install autoconf automake libtool curl make g++ unzip

git clone https://github.com/protocolbuffers/protobuf.git
cd protobuf
git submodule update --init --recursive
./autogen.sh

./configure
make
make check
sudo make install
sudo ldconfig

2. 編譯MNNConvert

以下兩種方法可用：

    (1) 執行以下命令：

cd MNN/tools/converter
./generate_schema.sh
mkdir build
cd build && cmake .. && make -j4

    (2) 在本地(rk3399)編譯時,先修改build_tool.sh中的 make -j16

#!/bin/bash

if [ -d "build" ]; then
  rm -rf build
fi
./generate_schema.sh

mkdir build
cd build

cmake ..
make clean
make -j4        # # #

3. 測試MNNConvert (模型轉換的使用)

cd MNN/tools/converter/build
./MNNConvert -h

4. 測試MNNDump2Json (MNNDump2Json)

    將MNN模型bin文件 dump 成可讀的類json格式文件，以方便對比原始模型參數

cd MNN/tools/converter/build
./MNNDump2Json.out ../../../benchmark/models/mobilenet_v1.caffe.mnn mobilenet_v1.caffe.json

三. 下載模型並使用MNNConvert (模型下載&轉換)

1. 下載並使用第二步得到的MNNConvert來轉換模型

cd MNN
./tools/script/get_model.sh

    下載的模型在/MNN/resource/model/ (應該沒記錯^_^)

2. 使用MNNConvert

    (1) Caffe2MNN

cd MNN/resource/build
./MNNConvert -f CAFFE --modelFile mobilenet_v1.caffe.caffemodel --prototxt mobilenet_v1.caffe.prototxt --MNNModel mobilenet_v1.caffe.mnn --bizCode MNN

    (2) TFLite2MNN

cd MNN/resource/build
./MNNConvert -f TFLITE --modelFile mobilenet_v2_1.0_224_quant.tflite --MNNModel mobilenet_v2_1.0_224_quant.tflite.mnn --bizCode MNN

    將mobilenet_v1.caffe.mnn，mobilenet_v2_1.0_224_quant.tflite.mnn複製到/MNN/benchmark/models/目錄下用於下面的測試。

四. 測試benchmark

cd MNN/build
./benchmark.out ../benchmark/models/ 10 0


# ------------------ output --------------------- #
MNN benchmark
Forward type: **CPU** thread=4** precision=2
--------> Benchmarking... loop = 10
[ - ] MobileNetV2_224.mnn         max =   92.516ms  min =   88.733ms  avg =   90.227ms
[ - ] mobilenet_v2_1.0_224_quant.tflite.mnn    max =   87.738ms  min =   84.411ms  avg =   85.817ms
[ - ] mobilenet_v1_quant.caffe.mnn    max =   75.278ms  min =   74.261ms  avg =   74.763ms
[ - ] inception-v3.mnn            max =  996.025ms  min =  807.543ms  avg =  863.333ms
[ - ] resnet-v2-50.mnn            max =  531.352ms  min =  445.743ms  avg =  473.887ms
[ - ] mobilenet-v1-1.0.mnn        max =  103.705ms  min =   93.981ms  avg =   96.573ms
[ - ] SqueezeNetV1.0.mnn          max =  193.273ms  min =  115.615ms  avg =  127.908ms
[ - ] mobilenet_v1.caffe.mnn      max =  107.799ms  min =   94.063ms  avg =   98.914ms
cd MNN/build
./benchmark.out ../benchmark/models/ 10 0


# ------------------ output --------------------- #
MNN benchmark
Forward type: **OpenCL** thread=4** precision=2
--------> Benchmarking... loop = 10
Can't Find type=3 backend, use 0 instead
[ - ] MobileNetV2_224.mnn         max =   92.939ms  min =   88.632ms  avg =   89.630ms
Can't Find type=3 backend, use 0 instead
[ - ] mobilenet_v2_1.0_224_quant.tflite.mnn    max =   89.197ms  min =   84.408ms  avg =   86.093ms
Can't Find type=3 backend, use 0 instead
[ - ] inception-v3.mnn            max =  870.511ms  min =  817.133ms  avg =  839.259ms
Can't Find type=3 backend, use 0 instead
[ - ] resnet-v2-50.mnn            max =  501.031ms  min =  448.233ms  avg =  462.990ms
Can't Find type=3 backend, use 0 instead
[ - ] mobilenet-v1-1.0.mnn        max =  107.135ms  min =   94.491ms  avg =   98.316ms
Can't Find type=3 backend, use 0 instead
[ - ] SqueezeNetV1.0.mnn          max =  124.856ms  min =  113.669ms  avg =  118.974ms
Can't Find type=3 backend, use 0 instead
[ - ] mobilenet_v1.caffe.mnn      max =  107.162ms  min =   94.707ms  avg =   98.140ms

    編譯MNN時，選擇option(MNN_OPENCL "Enable OpenCL" ON)，爲啥出現不能用OpenCL！！！

參考鏈接：https://github.com/alibaba/MNN

 

發表評論
所有評論
還沒有人評論，想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章

MNN量化源碼詳解

參考鏈接：https://www.zhihu.com/question/337513515 MNN量化工具使用 編譯 cd MNN mkdir build cd build cmake -DMNN_BUILD_QUANTO

三寸光阴___ 2020-07-08 08:51:38

MNN學習筆記

中文文檔 https://www.yuque.com/mnn/cn MNN安裝 MNN源碼：https://github.com/alibaba/MNN/tree/master/tools/converter 先安裝3.0以上版本

三寸光阴___ 2020-07-05 10:40:42

MNN windows 編譯

@MNN Windows編譯步驟 參考鏈接 https://www.yuque.com/mnn/cn/build_windows https://blog.csdn.net/ouyangfushu/article/details/

mikeyNa 2020-07-03 21:24:43

MNN模型存儲結構(flatbuffers)(轉)

FlatBuffers，MNN模型存儲結構基礎-------------https://www.jianshu.com/p/8eb153c12a4b Mnn模型存儲結構-------------https://www.jianshu.co

jjhhfb 2020-06-16 06:58:37

MNN windows環境編譯 c++.exe: error: /wd4267: No such file or directory

按照https://www.yuque.com/mnn/cn/build_windows編譯windows下的MNN cd /path/to/MNN powershell ./schema/generate.ps1 mkdir b

ystsaan 2020-06-16 02:48:50

MNN Resize error for ConvertTensor，The input is not ready，Can’t run session because not resized

背景： 使用vs2017編寫加載mnn模型並推理輸入圖片的程序，發生如下錯誤 The 321's input is not ready Resize error for 321, code=3 Resize error for C

ystsaan 2020-06-16 02:48:50

MNN深度框架學習教程（一） 編譯MNN，並跑通MNN的demo

實驗環境： 系統：Ubuntu18.04 硬件設備：PC設備和樹莓派4B 編譯教程：         MNN框架主要分爲三部分：推理，訓練和轉換。推理：在端側加載MNN模型進行推理的階段。訓練：訓練框架上，根據訓練數據訓練出模型的階段。轉

donkey_1993 2020-06-07 21:23:06

MNNConverter編譯錯誤: recipe for target 'tools/converter/CMakeFiles/MNNConverterONNX.dir/all' failed

ystsaan 2020-05-11 22:18:56

ONNX模型轉MNN模型中permute使用說明

wuqingshan2010 2020-04-29 10:43:51

MNN中Python示例

wuqingshan2010 2020-04-25 02:14:31

MNN中Python接口pymnn源碼編譯

wuqingshan2010 2020-04-25 02:14:31

windows 編譯 MNN 阿里inference框架

smart_well_ 2020-02-22 20:46:17

【MNN學習六】基於Android的MNN編譯安裝

@Vivian 2019-09-26 21:55:04

【MNN學習三】MNN可使用工具說明

@Vivia 2019-09-02 22:08:25

【MNN學習二】模型壓縮與量化

@Vivia 2019-09-02 22:08:25