Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "c6bca70296effc489df88aad8f77b91c063b217c"
Commit c99ee00b authored by liucong's avatar liucong
Browse files

修改部分代码和文档

parent 9cffb74e
Show whitespace changes
Inline Side-by-side
Showing with 74 additions and 1171 deletions
3rdParty/InstallOpenCVDependences.sh deleted 100644 → 0
View file @ 9cffb74e
#! /bin/sh
############### Ubuntu ###############
# 参考：https://docs.opencv.org/3.4.11/d7/d9f/tutorial_linux_install.html
# apt-get install build-essential -y
# apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev -y
# apt-get install python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc1394-22-dev -y # 处理图像所需的包，可选
############### CentOS ###############
yum install gcc gcc-c++ gtk2-devel gimp-devel gimp-devel-tools gimp-help-browser zlib-devel libtiff-devel libjpeg-devel libpng-devel gstreamer-devel libavc1394-devel libraw1394-devel libdc1394-devel jasper-devel jasper-utils swig python libtool nasm -y
\ No newline at end of file
CMakeLists.txt
View file @ c99ee00b
...@@ -2,7 +2,7 @@ ...@@ -2,7 +2,7 @@
cmake_minimum_required(VERSION 3.5) cmake_minimum_required(VERSION 3.5)
# 设置项目名 # 设置项目名
project(MIGraphX_Samples) project(GPT2)
# 设置编译器 # 设置编译器
set(CMAKE_CXX_COMPILER g++) set(CMAKE_CXX_COMPILER g++)
...@@ -12,7 +12,7 @@ set(CMAKE_BUILD_TYPE release) ...@@ -12,7 +12,7 @@ set(CMAKE_BUILD_TYPE release)
# 添加头文件路径 # 添加头文件路径
set(INCLUDE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/Src/ set(INCLUDE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/Src/
${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/ ${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/
${CMAKE_CURRENT_SOURCE_DIR}/Src/NLP/GPT2/ ${CMAKE_CURRENT_SOURCE_DIR}/Src/GPT2/
$ENV{DTKROOT}/include/ $ENV{DTKROOT}/include/
${CMAKE_CURRENT_SOURCE_DIR}/depend/include/) ${CMAKE_CURRENT_SOURCE_DIR}/depend/include/)
include_directories(${INCLUDE_PATH}) include_directories(${INCLUDE_PATH})
...@@ -23,11 +23,7 @@ set(LIBRARY_PATH ${CMAKE_CURRENT_SOURCE_DIR}/depend/lib64/ ...@@ -23,11 +23,7 @@ set(LIBRARY_PATH ${CMAKE_CURRENT_SOURCE_DIR}/depend/lib64/
link_directories(${LIBRARY_PATH}) link_directories(${LIBRARY_PATH})
# 添加依赖库 # 添加依赖库
set(LIBRARY opencv_core set(LIBRARY migraphx_ref
opencv_imgproc
opencv_imgcodecs
opencv_dnn
migraphx_ref
migraphx migraphx
migraphx_c migraphx_c
migraphx_device migraphx_device
...@@ -37,12 +33,11 @@ link_libraries(${LIBRARY}) ...@@ -37,12 +33,11 @@ link_libraries(${LIBRARY})
# 添加源文件 # 添加源文件
set(SOURCE_FILES ${CMAKE_CURRENT_SOURCE_DIR}/Src/main.cpp set(SOURCE_FILES ${CMAKE_CURRENT_SOURCE_DIR}/Src/main.cpp
${CMAKE_CURRENT_SOURCE_DIR}/Src/Sample.cpp ${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/tokenization.cpp
${CMAKE_CURRENT_SOURCE_DIR}/Src/NLP/GPT2/tokenization.cpp ${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/utf8proc.c
${CMAKE_CURRENT_SOURCE_DIR}/Src/NLP/GPT2/utf8proc.c ${CMAKE_CURRENT_SOURCE_DIR}/Src/GPT2/gpt2.cpp
${CMAKE_CURRENT_SOURCE_DIR}/Src/NLP/GPT2/GPT2.cpp
${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/CommonUtility.cpp ${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/CommonUtility.cpp
${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/Filesystem.cpp) ${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/Filesystem.cpp)
# 添加可执行目标 # 添加可执行目标
add_executable(MIGraphX_Samples ${SOURCE_FILES}) add_executable(GPT2 ${SOURCE_FILES})
Doc/Tutorial_Cpp/GPT2.md
View file @ c99ee00b
...@@ -27,11 +27,11 @@ GPT（Generative Pre-trained Transformer）系列模型以不断堆叠transforme ...@@ -27,11 +27,11 @@ GPT（Generative Pre-trained Transformer）系列模型以不断堆叠transforme
首先，根据提供的词汇表路径，通过cuBERT::FullTokenizer()函数加载词汇表，用于后续对输入文本的编码操作。其次，将词汇表中的内容依次保存到vector容器output中，用于数据后处理中的解码操作。 首先，根据提供的词汇表路径，通过cuBERT::FullTokenizer()函数加载词汇表，用于后续对输入文本的编码操作。其次，将词汇表中的内容依次保存到vector容器output中，用于数据后处理中的解码操作。
```c++ ```c++
cuBERT::FullTokenizer tokenizer = cuBERT::FullTokenizer("../Resource/Models/NLP/GPT2/vocab_shici.txt"); cuBERT::FullTokenizer tokenizer = cuBERT::FullTokenizer("../Resource/Models/vocab_shici.txt");
std::ifstream infile; std::ifstream infile;
std::string buf; std::string buf;
std::vector<std::string> output; std::vector<std::string> output;
infile.open("../Resource/Models/NLP/GPT2/vocab_shici.txt"); infile.open("../Resource/Models/vocab_shici.txt");
while (std::getline(infile,buf)) while (std::getline(infile,buf))
{ {
output.push_back(buf); output.push_back(buf);
...@@ -102,7 +102,7 @@ long unsigned int GPT2::Inference(const std::vector<long unsigned int> &input_id ...@@ -102,7 +102,7 @@ long unsigned int GPT2::Inference(const std::vector<long unsigned int> &input_id
inputShapes.push_back({1,input_id.size()}); inputShapes.push_back({1,input_id.size()});
// 输入数据 // 输入数据
migraphx::parameter_map inputData; std::unordered_map<std::string, migraphx::argument> inputData;
inputData[inputName]=migraphx::argument{migraphx::shape(inputShape.type(),inputShapes[0]),(long unsigned int*)input}; inputData[inputName]=migraphx::argument{migraphx::shape(inputShape.type(),inputShapes[0]),(long unsigned int*)input};
// 推理 // 推理
......
Doc/Tutorial_Python/GPT2.md
View file @ c99ee00b
...@@ -28,7 +28,7 @@ GPT（Generative Pre-trained Transformer）系列模型以不断堆叠的transfo ...@@ -28,7 +28,7 @@ GPT（Generative Pre-trained Transformer）系列模型以不断堆叠的transfo
```python ```python
# 加载词汇表 # 加载词汇表
vocab_file = os.path.join('../../../Resource/Models/NLP/GPT2', 'vocab_shici.txt') vocab_file = os.path.join('../../../Resource/Models', 'vocab_shici.txt')
tokenizer = BertTokenizerFast(vocab_file, sep_token="[SEP]", pad_token="[PAD]", cls_token="[CLS]") tokenizer = BertTokenizerFast(vocab_file, sep_token="[SEP]", pad_token="[PAD]", cls_token="[CLS]")
``` ```
...@@ -63,7 +63,7 @@ maxInput={"input":[1,1000]} ...@@ -63,7 +63,7 @@ maxInput={"input":[1,1000]}
for _ in range(max_len): for _ in range(max_len):
# 推理 # 推理
result = model.run({inputName: migraphx.argument(input_ids)}) result = model.run({inputName: input_ids})
logits = [float(x) for x in result[0].tolist()] logits = [float(x) for x in result[0].tolist()]
... ...
......
Python/NLP/GPT2/gpt2.py → Python/gpt2.py
View file @ c99ee00b
...@@ -5,7 +5,7 @@ import migraphx ...@@ -5,7 +5,7 @@ import migraphx
# 加载词汇表 # 加载词汇表
print("INFO: Complete loading the vocabulary") print("INFO: Complete loading the vocabulary")
vocab_file = os.path.join('../../../Resource/Models/NLP/GPT2', 'vocab_shici.txt') vocab_file = os.path.join('../Resource/Models', 'vocab_shici.txt')
tokenizer = BertTokenizerFast(vocab_file, sep_token="[SEP]", pad_token="[PAD]", cls_token="[CLS]") tokenizer = BertTokenizerFast(vocab_file, sep_token="[SEP]", pad_token="[PAD]", cls_token="[CLS]")
# 设置最大输入shape # 设置最大输入shape
...@@ -13,7 +13,7 @@ maxInput={"input":[1,1000]} ...@@ -13,7 +13,7 @@ maxInput={"input":[1,1000]}
# 加载模型 # 加载模型
print("INFO: Parsing and compiling the model") print("INFO: Parsing and compiling the model")
model = migraphx.parse_onnx("../../../Resource/Models/NLP/GPT2/GPT2_shici.onnx", map_input_dims=maxInput) model = migraphx.parse_onnx("../Resource/Models/GPT2_shici.onnx", map_input_dims=maxInput)
inputName=model.get_parameter_names()[0] inputName=model.get_parameter_names()[0]
inputShape=model.get_parameter_shapes()[inputName].lens() inputShape=model.get_parameter_shapes()[inputName].lens()
print("inputName:{0} \ninputShape:{1}".format(inputName,inputShape)) print("inputName:{0} \ninputShape:{1}".format(inputName,inputShape))
......
README.md
View file @ c99ee00b
...@@ -6,7 +6,11 @@ GPT2模型：第二代生成式预训练模型（Generative Pre-Training2）。 ...@@ -6,7 +6,11 @@ GPT2模型：第二代生成式预训练模型（Generative Pre-Training2）。
## 模型结构 ## 模型结构
GPT2主要使用Transformer的Decoder模块为特征提取器，并对Transformer Decoder进行了一些改动，原本的Decoder包含了两个Multi-Head Attention结构，而GPT2只保留了Mask Multi-Head Attention。 GPT2主要使用Transformer的Decoder模块为特征提取器，并对Transformer Decoder进行了一些改动，原本的Decoder包含了两个Multi-Head Attention结构，而GPT2只保留了Mask Multi-Head Attention。
## 构建安装 ## Python版本推理
本次采用GPT-2模型进行诗词生成任务，模型文件下载链接：https://pan.baidu.com/s/1KWeoUuakCZ5dualK69qCcw , 提取码：4pmh ，并将GPT2_shici.onnx模型文件保存在model文件夹下。下面介绍如何运行python代码示例，具体推理代码解析，在Doc/Tutorial_Python目录中有详细说明。
### 安装镜像
在光源可拉取推理的docker镜像，GPT2模型推理的镜像如下： 在光源可拉取推理的docker镜像，GPT2模型推理的镜像如下：
...@@ -14,13 +18,46 @@ GPT2主要使用Transformer的Decoder模块为特征提取器，并对Transforme ...@@ -14,13 +18,46 @@ GPT2主要使用Transformer的Decoder模块为特征提取器，并对Transforme
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1 docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
``` ```
### 安装Opencv依赖 ### 执行推理
1.参考《MIGraphX教程》中的安装方法安装MIGraphX并设置好PYTHONPATH
2.安装依赖：
```python ```python
# 进入migraphx samples工程根目录
cd <path_to_migraphx_samples> cd <path_to_migraphx_samples>
sh ./3rdParty/InstallOpenCVDependences.sh
# 进入示例程序目录
cd ./Python/
# 安装依赖
pip install -r requirements.txt
``` ```
3.设置环境变量：
```python
# 设置动态shape模式
export MIGRAPHX_DYNAMIC_SHAPE=1
```
4.在Python/NLP/GPT2目录下执行如下命令运行该示例程序：
```python
python gpt2.py
```
如下所示，采用交互式界面，通过输入开头诗词，GPT2模型可以生成后续的诗句。
<img src="./Doc/Images/GPT_03.png" style="zoom:80%;" align=middle>
## C++版本推理
下面介绍如何运行python代码示例，具体推理代码解析，在Doc/Tutorial_Cpp目录中有详细说明。
参考Python版本推理中的构建安装，在光源中拉取推理的docker镜像。
### 修改CMakeLists.txt ### 修改CMakeLists.txt
- 如果使用ubuntu系统，需要修改CMakeLists.txt中依赖库路径： - 如果使用ubuntu系统，需要修改CMakeLists.txt中依赖库路径：
...@@ -29,7 +66,7 @@ sh ./3rdParty/InstallOpenCVDependences.sh ...@@ -29,7 +66,7 @@ sh ./3rdParty/InstallOpenCVDependences.sh
- **MIGraphX2.3.0及以上版本需要c++17** - **MIGraphX2.3.0及以上版本需要c++17**
### 安装OpenCV并构建工程 ### 构建工程
``` ```
rbuild build -d depend rbuild build -d depend
...@@ -57,61 +94,22 @@ export LD_LIBRARY_PATH=<path_to_migraphx_samples>/depend/lib/:$LD_LIBRARY_PATH ...@@ -57,61 +94,22 @@ export LD_LIBRARY_PATH=<path_to_migraphx_samples>/depend/lib/:$LD_LIBRARY_PATH
source ~/.bashrc source ~/.bashrc
``` ```
## 推理 ### 执行推理
本次采用GPT-2模型进行诗词生成任务，模型文件下载链接：https://pan.baidu.com/s/1KWeoUuakCZ5dualK69qCcw , 提取码：4pmh ，并将GPT2_shici.onnx模型文件保存在model文件夹下。下面介绍如何运行python代码和C++代码示例，具体推理代码解析，在Doc目录中有详细说明。
### python版本推理 运行GPT2示例程序，具体执行如下命令：
1.参考《MIGraphX教程》中的安装方法安装MIGraphX并设置好PYTHONPATH
2.安装依赖：
```python ```python
# 进入migraphx samples工程根目录 # 进入migraphx samples工程根目录
cd <path_to_migraphx_samples> cd <path_to_migraphx_samples>
# 进入示例程序目录 # 进入build目录
cd Python/NLP/GPT2
# 安装依赖
pip install -r requirements.txt
```
3.设置环境变量：
```python
# 设置动态shape模式
export MIGRAPHX_DYNAMIC_SHAPE=1
```
4.在Python/NLP/GPT2目录下执行如下命令运行该示例程序：
```python
python gpt2.py
```
如下所示，采用交互式界面，通过输入开头诗词，GPT2模型可以生成后续的诗句。
<img src="./Doc/Images/GPT_03.png" style="zoom:80%;" align=middle>
### C++版本推理
切换到build目录中，执行如下命令：
```python
cd ./build/ cd ./build/
./MIGraphX_Samples
```
根据提示选择运行GPT2模型的示例程序
```python
# 设置动态shape模式 # 设置动态shape模式
export MIGRAPHX_DYNAMIC_SHAPE=1 export MIGRAPHX_DYNAMIC_SHAPE=1
# 运行示例 # 执行示例程序
./MIGraphX_Samples 0 ./GPT2
``` ```
如下所示，采用交互式界面，通过输入开头诗词，GPT2模型可以推理出后续的诗句。 如下所示，采用交互式界面，通过输入开头诗词，GPT2模型可以推理出后续的诗句。
......
Resource/Configuration.xml deleted 100644 → 0
View file @ 9cffb74e
<?xml version="1.0" encoding="GB2312"?>
<opencv_storage>
<!--GPT2-->
<GPT2>
<ModelPath>"../Resource/Models/NLP/GPT2/GPT2_shici.onnx"</ModelPath>
</GPT2>
</opencv_storage>
Src/NLP/GPT2/GPT2.cpp → Src/GPT2/gpt2.cpp
View file @ c99ee00b
...@@ -2,65 +2,44 @@ ...@@ -2,65 +2,44 @@
#include <sstream> #include <sstream>
#include <migraphx/onnx.hpp> #include <migraphx/onnx.hpp>
#include <migraphx/gpu/target.hpp> #include <migraphx/gpu/target.hpp>
#include <migraphx/gpu/hip.hpp>
#include <migraphx/generate.hpp>
#include <migraphx/quantization.hpp>
#include <migraphx/reshape2.hpp> #include <migraphx/reshape2.hpp>
#include <CommonUtility.h>
#include <Filesystem.h>
#include <SimpleLog.h> #include <SimpleLog.h>
#include <algorithm> #include <algorithm>
#include <string> #include <string>
#include <vector>
#include <stdexcept> #include <stdexcept>
#include <GPT2.h> #include <gpt2.h>
#include <tokenization.h> #include <tokenization.h>
namespace migraphxSamples namespace migraphxSamples
{ {
GPT2::GPT2():logFile(NULL) GPT2::GPT2()
{ {
} }
GPT2::~GPT2() GPT2::~GPT2()
{ {
configurationFile.release();
} }
ErrorCode GPT2::Initialize(InitializationParameterOfNLP initParamOfNLPGPT2) ErrorCode GPT2::Initialize(InitializationParameterOfNLP initParamOfNLPGPT2)
{ {
// 初始化(获取日志文件,加载配置文件等) // 设置模型路径
ErrorCode errorCode=DoCommonInitialization(initParamOfNLPGPT2); std::string modelPath="../Resource/Models/GPT2_shici.onnx";
if(errorCode!=SUCCESS)
{
LOG_ERROR(logFile,"fail to DoCommonInitialization\n");
return errorCode;
}
LOG_INFO(logFile,"succeed to DoCommonInitialization\n");
// 获取配置文件参数
FileNode netNode = configurationFile["GPT2"];
std::string modelPath=initializationParameter.parentPath+(std::string)netNode["ModelPath"];
// 设置最大输入shape // 设置最大输入shape
migraphx::onnx_options onnx_options; migraphx::onnx_options onnx_options;
onnx_options.map_input_dims["input"]={1,1000}; onnx_options.map_input_dims["input"]={1,1000};
// 加载模型 // 加载模型
if(Exists(modelPath)==false)
{
LOG_ERROR(logFile,"%s not exist!\n",modelPath.c_str());
return MODEL_NOT_EXIST;
}
net = migraphx::parse_onnx(modelPath, onnx_options); net = migraphx::parse_onnx(modelPath, onnx_options);
LOG_INFO(logFile,"succeed to load model: %s\n",GetFileName(modelPath).c_str()); LOG_INFO(stdout,"succeed to load model: GPT2_shici\n");
// 获取模型输入属性 // 获取模型输入属性
std::pair<std::string, migraphx::shape> inputAttribute=*(net.get_parameter_shapes().begin()); std::unordered_map<std::string, migraphx::shape> inputMap=net.get_parameter_shapes();
inputName=inputAttribute.first; inputName=inputMap.begin()->first;
inputShape=inputAttribute.second; inputShape=inputMap.begin()->second;
// 设置模型为GPU模式 // 设置模型为GPU模式
migraphx::target gpuTarget = migraphx::gpu::target{}; migraphx::target gpuTarget = migraphx::gpu::target{};
...@@ -68,43 +47,10 @@ ErrorCode GPT2::Initialize(InitializationParameterOfNLP initParamOfNLPGPT2) ...@@ -68,43 +47,10 @@ ErrorCode GPT2::Initialize(InitializationParameterOfNLP initParamOfNLPGPT2)
// 编译模型 // 编译模型
migraphx::compile_options options; migraphx::compile_options options;
options.device_id=0; // 设置GPU设备，默认为0号设备 options.device_id=0; // 设置GPU设备，默认为0号设备
options.offload_copy=true; // 设置offload_copy options.offload_copy=true;
net.compile(gpuTarget,options); net.compile(gpuTarget,options);
LOG_INFO(logFile,"succeed to compile model: %s\n",GetFileName(modelPath).c_str()); LOG_INFO(stdout,"succeed to compile model: %s\n");
return SUCCESS;
}
ErrorCode GPT2::DoCommonInitialization(InitializationParameterOfNLP initParamOfNLPGPT2)
{
initializationParameter = initParamOfNLPGPT2;
// 获取日志文件
logFile=LogManager::GetInstance()->GetLogFile(initializationParameter.logName);
// 加载配置文件
std::string configFilePath=initializationParameter.configFilePath;
if(!Exists(configFilePath))
{
LOG_ERROR(logFile, "no configuration file!\n");
return CONFIG_FILE_NOT_EXIST;
}
if(!configurationFile.open(configFilePath, FileStorage::READ))
{
LOG_ERROR(logFile, "fail to open configuration file\n");
return FAIL_TO_OPEN_CONFIG_FILE;
}
LOG_INFO(logFile, "succeed to open configuration file\n");
// 修改父路径
std::string &parentPath = initializationParameter.parentPath;
if (!parentPath.empty())
{
if(!IsPathSeparator(parentPath[parentPath.size() - 1]))
{
parentPath+=PATH_SEPARATOR;
}
}
return SUCCESS; return SUCCESS;
} }
...@@ -127,7 +73,7 @@ long unsigned int GPT2::Inference(const std::vector<long unsigned int> &input_id ...@@ -127,7 +73,7 @@ long unsigned int GPT2::Inference(const std::vector<long unsigned int> &input_id
inputShapes.push_back({1,input_id.size()}); inputShapes.push_back({1,input_id.size()});
// 输入数据 // 输入数据
migraphx::parameter_map inputData; std::unordered_map<std::string, migraphx::argument> inputData;
inputData[inputName]=migraphx::argument{migraphx::shape(inputShape.type(),inputShapes[0]),(long unsigned int*)input}; inputData[inputName]=migraphx::argument{migraphx::shape(inputShape.type(),inputShapes[0]),(long unsigned int*)input};
// 推理 // 推理
......
Src/NLP/GPT2/GPT2.h → Src/GPT2/gpt2.h
View file @ c99ee00b
...@@ -6,7 +6,6 @@ ...@@ -6,7 +6,6 @@
#include <migraphx/program.hpp> #include <migraphx/program.hpp>
#include <CommonDefinition.h> #include <CommonDefinition.h>
#include <tokenization.h> #include <tokenization.h>
using namespace cuBERT;
namespace migraphxSamples namespace migraphxSamples
{ {
...@@ -24,7 +23,7 @@ public: ...@@ -24,7 +23,7 @@ public:
~GPT2(); ~GPT2();
ErrorCode Initialize(InitializationParameterOfNLP initParamOfNLPGPT2); ErrorCode Initialize();
ErrorCode Preprocessing(cuBERT::FullTokenizer tokenizer, ErrorCode Preprocessing(cuBERT::FullTokenizer tokenizer,
char *question, char *question,
...@@ -33,13 +32,6 @@ public: ...@@ -33,13 +32,6 @@ public:
long unsigned int Inference(const std::vector<long unsigned int> &input_id); long unsigned int Inference(const std::vector<long unsigned int> &input_id);
private: private:
ErrorCode DoCommonInitialization(InitializationParameterOfNLP initParamOfNLPGPT2);
private:
FILE *logFile;
cv::FileStorage configurationFile;
InitializationParameterOfNLP initializationParameter;
migraphx::program net; migraphx::program net;
std::string inputName; std::string inputName;
migraphx::shape inputShape; migraphx::shape inputShape;
......
Src/Sample.cpp deleted 100644 → 0
View file @ 9cffb74e
#include <Sample.h>
#include <SimpleLog.h>
#include <GPT2.h>
#include <tokenization.h>
#include <fstream>
using namespace std;
using namespace migraphx;
using namespace migraphxSamples;
void Sample_GPT2()
{
// 加载GPT2模型
GPT2 gpt2;
InitializationParameterOfNLP initParamOfNLPGPT2;
initParamOfNLPGPT2.parentPath = "";
initParamOfNLPGPT2.configFilePath = CONFIG_FILE;
initParamOfNLPGPT2.logName = "";
ErrorCode errorCode = gpt2.Initialize(initParamOfNLPGPT2);
if (errorCode != SUCCESS)
{
LOG_ERROR(stdout, "fail to initialize GPT2!\n");
exit(-1);
}
LOG_INFO(stdout, "succeed to initialize GPT2\n");
// 加载词汇表，用于编码和解码
cuBERT::FullTokenizer tokenizer = cuBERT::FullTokenizer("../Resource/Models/NLP/GPT2/vocab_shici.txt");
std::ifstream infile;
std::string buf;
std::vector<std::string> output;
infile.open("../Resource/Models/NLP/GPT2/vocab_shici.txt");
while (std::getline(infile,buf))
{
output.push_back(buf);
}
std::vector<long unsigned int> input_id;
char question[100];
std::vector<long unsigned int> score;
std::vector<std::string> result;
std::cout << "开始和GPT2对诗，输入CTRL + Z以退出" << std::endl;
while (true)
{
// 数据预处理
std::cout << "question: ";
cin.getline(question, 100);
gpt2.Preprocessing(tokenizer, question, input_id);
// 推理
for(int i=0;i<50;++i)
{
long unsigned int outputs = gpt2.Inference(input_id);
if(outputs == 102)
{
break;
}
input_id.push_back(outputs);
score.push_back(outputs);
}
// 将数值映射为字符
for(int i=0;i<score.size();++i)
{
result.push_back(output[score[i]]);
}
// 打印结果
std::cout << "chatbot: ";
std::cout << question;
for(int j=0; j<result.size();++j)
{
std::cout << result[j];
}
std::cout << std::endl;
// 清除数据
input_id.clear();
result.clear();
score.clear();
}
}
Src/Sample.h deleted 100644 → 0
View file @ 9cffb74e
// 示例程序
#ifndef __SAMPLE_H__
#define __SAMPLE_H__
// GPT2 Dynamic sample
void Sample_GPT2();
#endif
\ No newline at end of file
Src/Utility/CommonUtility.cpp deleted 100644 → 0
View file @ 9cffb74e
#include <CommonUtility.h>
#include <assert.h>
#include <ctype.h>
#include <time.h>
#include <stdlib.h>
#include <algorithm>
#include <sstream>
#include <vector>
#ifdef _WIN32
#include <io.h>
#include <direct.h>
#include <Windows.h>
#else
#include <unistd.h>
#include <dirent.h>
#include <sys/stat.h>
#include <sys/time.h>
#endif
#include <SimpleLog.h>
namespace migraphxSamples
{
_Time GetCurrentTime3()
{
_Time currentTime;
#if (defined WIN32 || defined _WIN32)
SYSTEMTIME systemTime;
GetLocalTime(&systemTime);
char temp[8] = { 0 };
sprintf(temp, "%04d", systemTime.wYear);
currentTime.year=string(temp);
sprintf(temp, "%02d", systemTime.wMonth);
currentTime.month=string(temp);
sprintf(temp, "%02d", systemTime.wDay);
currentTime.day=string(temp);
sprintf(temp, "%02d", systemTime.wHour);
currentTime.hour=string(temp);
sprintf(temp, "%02d", systemTime.wMinute);
currentTime.minute=string(temp);
sprintf(temp, "%02d", systemTime.wSecond);
currentTime.second=string(temp);
sprintf(temp, "%03d", systemTime.wMilliseconds);
currentTime.millisecond=string(temp);
sprintf(temp, "%d", systemTime.wDayOfWeek);
currentTime.weekDay=string(temp);
#else
struct timeval tv;
struct tm *p;
gettimeofday(&tv, NULL);
p = localtime(&tv.tv_sec);
char temp[8]={0};
sprintf(temp,"%04d",1900+p->tm_year);
currentTime.year=string(temp);
sprintf(temp,"%02d",1+p->tm_mon);
currentTime.month=string(temp);
sprintf(temp,"%02d",p->tm_mday);
currentTime.day=string(temp);
sprintf(temp,"%02d",p->tm_hour);
currentTime.hour=string(temp);
sprintf(temp,"%02d",p->tm_min);
currentTime.minute=string(temp);
sprintf(temp,"%02d",p->tm_sec);
currentTime.second=string(temp);
sprintf(temp,"%03d",tv.tv_usec/1000);
currentTime.millisecond = string(temp);
sprintf(temp, "%03d", tv.tv_usec % 1000);
currentTime.microsecond = string(temp);
sprintf(temp, "%d", p->tm_wday);
currentTime.weekDay = string(temp);
#endif
return currentTime;
}
std::vector<std::string> SplitString(std::string str, std::string separator)
{
std::string::size_type pos;
std::vector<std::string> result;
str+=separator;//扩展字符串以方便操作
int size=str.size();
for(int i=0; i<size; i++)
{
pos=str.find(separator,i);
if(pos<size)
{
std::string s=str.substr(i,pos-i);
result.push_back(s);
i=pos+separator.size()-1;
}
}
return result;
}
bool CompareConfidence(const ResultOfDetection &L,const ResultOfDetection &R)
{
return L.confidence > R.confidence;
}
bool CompareArea(const ResultOfDetection &L,const ResultOfDetection &R)
{
return L.boundingBox.area() > R.boundingBox.area();
}
void NMS(vector<ResultOfDetection> &detections, float IOUThreshold)
{
// sort
std::sort(detections.begin(), detections.end(), CompareConfidence);
for (int i = 0; i<detections.size(); ++i)
{
if (detections[i].exist)
{
for (int j = i + 1; j<detections.size(); ++j)
{
if (detections[j].exist)
{
// compute IOU
float intersectionArea = (detections[i].boundingBox & detections[j].boundingBox).area();
float intersectionRate = intersectionArea / (detections[i].boundingBox.area() + detections[j].boundingBox.area() - intersectionArea);
if (intersectionRate>IOUThreshold)
{
detections[j].exist = false;
}
}
}
}
}
}
}
Src/Utility/CommonUtility.h deleted 100644 → 0
View file @ 9cffb74e
// 常用工具
#ifndef __COMMON_UTILITY_H__
#define __COMMON_UTILITY_H__
#include <mutex>
#include <string>
#include <vector>
#include <CommonDefinition.h>
using namespace std;
namespace migraphxSamples
{
// 分割字符串
std::vector<std::string> SplitString(std::string str,std::string separator);
// 排序规则: 按照置信度或者按照面积排序
bool CompareConfidence(const ResultOfDetection &L,const ResultOfDetection &R);
bool CompareArea(const ResultOfDetection &L,const ResultOfDetection &R);
void NMS(std::vector<ResultOfDetection> &detections, float IOUThreshold);
}
#endif
Src/Utility/Filesystem.cpp deleted 100644 → 0
View file @ 9cffb74e
#include <Filesystem.h>
#include <algorithm>
#include <sys/stat.h>
#include <sys/types.h>
#include <fstream>
#ifdef _WIN32
#include <io.h>
#include <direct.h>
#include <Windows.h>
#else
#include <unistd.h>
#include <dirent.h>
#endif
#include <CommonUtility.h>
#include <opencv2/opencv.hpp>
#include <SimpleLog.h>
using namespace cv;
// 路径分隔符(Linux:‘/’,Windows:’\\’)
#ifdef _WIN32
#define PATH_SEPARATOR '\\'
#else
#define PATH_SEPARATOR '/'
#endif
namespace migraphxSamples
{
#if defined _WIN32 || defined WINCE
const char dir_separators[] = "/\\";
struct dirent
{
const char* d_name;
};
struct DIR
{
#ifdef WINRT
WIN32_FIND_DATAW data;
#else
WIN32_FIND_DATAA data;
#endif
HANDLE handle;
dirent ent;
#ifdef WINRT
DIR() { }
~DIR()
{
if (ent.d_name)
delete[] ent.d_name;
}
#endif
};
DIR* opendir(const char* path)
{
DIR* dir = new DIR;
dir->ent.d_name = 0;
#ifdef WINRT
string full_path = string(path) + "\\*";
wchar_t wfull_path[MAX_PATH];
size_t copied = mbstowcs(wfull_path, full_path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
dir->handle = ::FindFirstFileExW(wfull_path, FindExInfoStandard,
&dir->data, FindExSearchNameMatch, NULL, 0);
#else
dir->handle = ::FindFirstFileExA((string(path) + "\\*").c_str(),
FindExInfoStandard, &dir->data, FindExSearchNameMatch, NULL, 0);
#endif
if (dir->handle == INVALID_HANDLE_VALUE)
{
/*closedir will do all cleanup*/
delete dir;
return 0;
}
return dir;
}
dirent* readdir(DIR* dir)
{
#ifdef WINRT
if (dir->ent.d_name != 0)
{
if (::FindNextFileW(dir->handle, &dir->data) != TRUE)
return 0;
}
size_t asize = wcstombs(NULL, dir->data.cFileName, 0);
CV_Assert((asize != 0) && (asize != (size_t)-1));
char* aname = new char[asize + 1];
aname[asize] = 0;
wcstombs(aname, dir->data.cFileName, asize);
dir->ent.d_name = aname;
#else
if (dir->ent.d_name != 0)
{
if (::FindNextFileA(dir->handle, &dir->data) != TRUE)
return 0;
}
dir->ent.d_name = dir->data.cFileName;
#endif
return &dir->ent;
}
void closedir(DIR* dir)
{
::FindClose(dir->handle);
delete dir;
}
#else
# include <dirent.h>
# include <sys/stat.h>
const char dir_separators[] = "/";
#endif
static bool isDir(const string &path, DIR* dir)
{
#if defined _WIN32 || defined WINCE
DWORD attributes;
BOOL status = TRUE;
if (dir)
attributes = dir->data.dwFileAttributes;
else
{
WIN32_FILE_ATTRIBUTE_DATA all_attrs;
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
status = ::GetFileAttributesExW(wpath, GetFileExInfoStandard, &all_attrs);
#else
status = ::GetFileAttributesExA(path.c_str(), GetFileExInfoStandard, &all_attrs);
#endif
attributes = all_attrs.dwFileAttributes;
}
return status && ((attributes & FILE_ATTRIBUTE_DIRECTORY) != 0);
#else
(void)dir;
struct stat stat_buf;
if (0 != stat(path.c_str(), &stat_buf))
return false;
int is_dir = S_ISDIR(stat_buf.st_mode);
return is_dir != 0;
#endif
}
bool IsDirectory(const string &path)
{
return isDir(path, NULL);
}
bool Exists(const string& path)
{
#if defined _WIN32 || defined WINCE
BOOL status = TRUE;
{
WIN32_FILE_ATTRIBUTE_DATA all_attrs;
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
status = ::GetFileAttributesExW(wpath, GetFileExInfoStandard, &all_attrs);
#else
status = ::GetFileAttributesExA(path.c_str(), GetFileExInfoStandard, &all_attrs);
#endif
}
return !!status;
#else
struct stat stat_buf;
return (0 == stat(path.c_str(), &stat_buf));
#endif
}
bool IsPathSeparator(char c)
{
return c == '/' || c == '\\';
}
string JoinPath(const string& base, const string& path)
{
if (base.empty())
return path;
if (path.empty())
return base;
bool baseSep = IsPathSeparator(base[base.size() - 1]);
bool pathSep = IsPathSeparator(path[0]);
string result;
if (baseSep && pathSep)
{
result = base + path.substr(1);
}
else if (!baseSep && !pathSep)
{
result = base + PATH_SEPARATOR + path;
}
else
{
result = base + path;
}
return result;
}
static bool wildcmp(const char *string, const char *wild)
{
const char *cp = 0, *mp = 0;
while ((*string) && (*wild != '*'))
{
if ((*wild != *string) && (*wild != '?'))
{
return false;
}
wild++;
string++;
}
while (*string)
{
if (*wild == '*')
{
if (!*++wild)
{
return true;
}
mp = wild;
cp = string + 1;
}
else if ((*wild == *string) || (*wild == '?'))
{
wild++;
string++;
}
else
{
wild = mp;
string = cp++;
}
}
while (*wild == '*')
{
wild++;
}
return *wild == 0;
}
static void glob_rec(const string &directory, const string& wildchart, std::vector<string>& result,
bool recursive, bool includeDirectories, const string& pathPrefix)
{
DIR *dir;
if ((dir = opendir(directory.c_str())) != 0)
{
/* find all the files and directories within directory */
try
{
struct dirent *ent;
while ((ent = readdir(dir)) != 0)
{
const char* name = ent->d_name;
if ((name[0] == 0) || (name[0] == '.' && name[1] == 0) || (name[0] == '.' && name[1] == '.' && name[2] == 0))
continue;
string path = JoinPath(directory, name);
string entry = JoinPath(pathPrefix, name);
if (isDir(path, dir))
{
if (recursive)
glob_rec(path, wildchart, result, recursive, includeDirectories, entry);
if (!includeDirectories)
continue;
}
if (wildchart.empty() || wildcmp(name, wildchart.c_str()))
result.push_back(entry);
}
}
catch (...)
{
closedir(dir);
throw;
}
closedir(dir);
}
else
{
LOG_INFO(stdout, "could not open directory: %s", directory.c_str());
}
}
void GetFileNameList(const string &directory, const string &pattern, std::vector<string>& result, bool recursive, bool addPath)
{
// split pattern
vector<string> patterns=SplitString(pattern,",");
result.clear();
for(int i=0;i<patterns.size();++i)
{
string eachPattern=patterns[i];
std::vector<string> eachResult;
glob_rec(directory, eachPattern, eachResult, recursive, true, directory);
for(int j=0;j<eachResult.size();++j)
{
if (IsDirectory(eachResult[j]))
continue;
if(addPath)
{
result.push_back(eachResult[j]);
}
else
{
result.push_back(GetFileName(eachResult[j]));
}
}
}
std::sort(result.begin(), result.end());
}
void GetFileNameList2(const string &directory, const string &pattern, std::vector<string>& result, bool recursive, bool addPath)
{
// split pattern
vector<string> patterns = SplitString(pattern, ",");
result.clear();
for (int i = 0; i<patterns.size(); ++i)
{
string eachPattern = patterns[i];
std::vector<string> eachResult;
glob_rec(directory, eachPattern, eachResult, recursive, true, directory);
for (int j = 0; j<eachResult.size(); ++j)
{
string filePath = eachResult[j];
if (IsDirectory(filePath))
{
filePath = filePath + "/";
for (int k = 0; k < filePath.size(); ++k)
{
if (IsPathSeparator(filePath[k]))
{
filePath[k] = '/';
}
}
}
if (addPath)
{
result.push_back(filePath);
}
else
{
if (!IsDirectory(filePath))
{
result.push_back(GetFileName(filePath));
}
}
}
}
std::sort(result.begin(), result.end());
}
void RemoveAll(const string& path)
{
if (!Exists(path))
return;
if (IsDirectory(path))
{
std::vector<string> entries;
GetFileNameList2(path, string(), entries, false, true);
for (size_t i = 0; i < entries.size(); i++)
{
const string& e = entries[i];
RemoveAll(e);
}
#ifdef _MSC_VER
bool result = _rmdir(path.c_str()) == 0;
#else
bool result = rmdir(path.c_str()) == 0;
#endif
if (!result)
{
LOG_INFO(stdout, "can't remove directory: %s\n", path.c_str());
}
}
else
{
#ifdef _MSC_VER
bool result = _unlink(path.c_str()) == 0;
#else
bool result = unlink(path.c_str()) == 0;
#endif
if (!result)
{
LOG_INFO(stdout, "can't remove file: %s\n", path.c_str());
}
}
}
void Remove(const string &directory, const string &extension)
{
DIR *dir;
static int numberOfFiles = 0;
if ((dir = opendir(directory.c_str())) != 0)
{
/* find all the files and directories within directory */
try
{
struct dirent *ent;
while ((ent = readdir(dir)) != 0)
{
const char* name = ent->d_name;
if ((name[0] == 0) || (name[0] == '.' && name[1] == 0) || (name[0] == '.' && name[1] == '.' && name[2] == 0))
continue;
string path = JoinPath(directory, name);
if (isDir(path, dir))
{
Remove(path, extension);
}
// �ж���չ��
if (extension.empty() || wildcmp(name, extension.c_str()))
{
RemoveAll(path);
++numberOfFiles;
LOG_INFO(stdout, "%s deleted! number of deleted files:%d\n", path.c_str(), numberOfFiles);
}
}
}
catch (...)
{
closedir(dir);
throw;
}
closedir(dir);
}
else
{
LOG_INFO(stdout, "could not open directory: %s", directory.c_str());
}
// ����RemoveAllɾ��Ŀ¼
RemoveAll(directory);
}
string GetFileName(const string &path)
{
string fileName;
int indexOfPathSeparator = -1;
for (int i = path.size() - 1; i >= 0; --i)
{
if (IsPathSeparator(path[i]))
{
fileName = path.substr(i + 1, path.size() - i - 1);
indexOfPathSeparator = i;
break;
}
}
if (indexOfPathSeparator == -1)
{
fileName = path;
}
return fileName;
}
string GetFileName_NoExtension(const string &path)
{
string fileName=GetFileName(path);
string fileName_NoExtension;
for(int i=fileName.size()-1;i>0;--i)
{
if(fileName[i]=='.')
{
fileName_NoExtension=fileName.substr(0,i);
break;
}
}
return fileName_NoExtension;
}
string GetExtension(const string &path)
{
string fileName;
for (int i = path.size() - 1; i >= 0; --i)
{
if (path[i]=='.')
{
fileName = path.substr(i, path.size() - i);
break;
}
}
return fileName;
}
string GetParentPath(const string &path)
{
string fileName;
for (int i = path.size() - 1; i >= 0; --i)
{
if (IsPathSeparator(path[i]))
{
fileName = path.substr(0, i+1);
break;
}
}
return fileName;
}
static bool CreateDirectory(const string &path)
{
#if defined WIN32 || defined _WIN32 || defined WINCE
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
int result = CreateDirectoryA(wpath, NULL) ? 0 : -1;
#else
int result = _mkdir(path.c_str());
#endif
#elif defined __linux__ || defined __APPLE__
int result = mkdir(path.c_str(), 0777);
#else
int result = -1;
#endif
if (result == -1)
{
return IsDirectory(path);
}
return true;
}
bool CreateDirectories(const string &directoryPath)
{
string path = directoryPath;
for (;;)
{
char last_char = path.empty() ? 0 : path[path.length() - 1];
if (IsPathSeparator(last_char))
{
path = path.substr(0, path.length() - 1);
continue;
}
break;
}
if (path.empty() || path == "./" || path == ".\\" || path == ".")
return true;
if (IsDirectory(path))
return true;
size_t pos = path.rfind('/');
if (pos == string::npos)
pos = path.rfind('\\');
if (pos != string::npos)
{
string parent_directory = path.substr(0, pos);
if (!parent_directory.empty())
{
if (!CreateDirectories(parent_directory))
return false;
}
}
return CreateDirectory(path);
}
bool CopyFile(const string srcPath, const string dstPath)
{
std::ifstream srcFile(srcPath,ios::binary);
std::ofstream dstFile(dstPath,ios::binary);
if(!srcFile.is_open())
{
LOG_ERROR(stdout,"can not open %s\n",srcPath.c_str());
return false;
}
if(!dstFile.is_open())
{
LOG_ERROR(stdout, "can not open %s\n", dstPath.c_str());
return false;
}
if(srcPath==dstPath)
{
LOG_ERROR(stdout, "src can not be same with dst\n");
return false;
}
char buffer[2048];
unsigned int numberOfBytes=0;
while(srcFile)
{
srcFile.read(buffer,2048);
dstFile.write(buffer,srcFile.gcount());
numberOfBytes+=srcFile.gcount();
}
srcFile.close();
dstFile.close();
return true;
}
bool CopyDirectories(string srcPath, const string dstPath)
{
if(srcPath==dstPath)
{
LOG_ERROR(stdout, "src can not be same with dst\n");
return false;
}
// ȥ������·���ָ���
srcPath = srcPath.substr(0, srcPath.size() - 1);
vector<string> fileNameList;
GetFileNameList2(srcPath, "", fileNameList, true, true);
string parentPathOfSrc=GetParentPath(srcPath);
int length=parentPathOfSrc.size();
// create all directories
for(int i=0;i<fileNameList.size();++i)
{
// create directory
string srcFilePath=fileNameList[i];
string subStr=srcFilePath.substr(length,srcFilePath.size()-length);
string dstFilePath=dstPath+subStr;
string parentPathOfDst=GetParentPath(dstFilePath);
CreateDirectories(parentPathOfDst);
}
// copy file
for(int i=0;i<fileNameList.size();++i)
{
string srcFilePath=fileNameList[i];
if (IsDirectory(srcFilePath))
{
continue;
}
string subStr=srcFilePath.substr(length,srcFilePath.size()-length);
string dstFilePath=dstPath+subStr;
// copy file
CopyFile(srcFilePath,dstFilePath);
// process
double process = (1.0*(i + 1) / fileNameList.size()) * 100;
LOG_INFO(stdout, "%s done! %f% \n", GetFileName(fileNameList[i]).c_str(), process);
}
LOG_INFO(stdout, "all done!(the number of files:%d)\n", fileNameList.size());
return true;
}
}
Src/Utility/Filesystem.h deleted 100644 → 0
View file @ 9cffb74e
// 文件以及目录处理
#ifndef __FILE_SYSTEM_H__
#define __FILE_SYSTEM_H__
#include <vector>
#include <string>
using namespace std;
namespace migraphxSamples
{
// 路径是否存在
bool Exists(const std::string &path);
// 路径是否为目录
bool IsDirectory(const std::string &path);
// 是否是路径分隔符(Linux:‘/’,Windows:’\\’)
bool IsPathSeparator(char c);
// 路径拼接
string JoinPath(const std::string &base, const std::string &path);
// 创建多级目录,注意：创建多级目录的时候，目标目录是不能有文件存在的
bool CreateDirectories(const std::string &directoryPath);
/** 生成符合指定模式的文件名列表(支持递归遍历)
*
* pattern: 模式,比如"*.jpg","*.png","*.jpg,*.png"
* addPath：是否包含父路径
* 注意：
1. 多个模式使用","分割,比如"*.jpg,*.png"
2. 支持通配符'*','?' ,比如第一个字符是7的所有文件名:"7*.*", 以512结尾的所有jpg文件名："*512.jpg"
3. 使用"*.jpg"，而不是".jpg"
4. 空string表示返回所有结果
5. 不能返回子目录名
*
*/
void GetFileNameList(const std::string &directory, const std::string &pattern, std::vector<std::string> &result, bool recursive, bool addPath);
// 与GetFileNameList的区别在于如果有子目录，在addPath为true的时候会返回子目录路径(目录名最后有"/")
void GetFileNameList2(const std::string &directory, const std::string &pattern, std::vector<std::string> &result, bool recursive, bool addPath);
// 删除文件或者目录,支持递归删除
void Remove(const std::string &directory, const std::string &extension="");
/** 获取路径的文件名和扩展名
*
* 示例：path为D:/1/1.txt,则GetFileName()为1.txt,GetFileName_NoExtension()为1,GetExtension()为.txt,GetParentPath()为D:/1/
*/
string GetFileName(const std::string &path); // 1.txt
string GetFileName_NoExtension(const std::string &path); // 1
string GetExtension(const std::string &path);// .txt
string GetParentPath(const std::string &path);// D:/1/
// 拷贝文件:CopyFile("D:/1.txt","D:/2.txt");将1.txt拷贝为2.txt
bool CopyFile(const std::string srcPath,const std::string dstPath);
/** 拷贝目录
*
* 示例：CopyDirectories("D:/0/1/2/","E:/3/");实现把D:/0/1/2/目录拷贝到E:/3/目录中(即拷贝完成后的目录结构为E:/3/2/)
* 注意：
1.第一个参数的最后不能加”/”
2.不能拷贝隐藏文件
*/
bool CopyDirectories(std::string srcPath,const std::string dstPath);
}
#endif
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment