diff --git a/tutorials/source_en/advanced_use/images/side_infer_process.png b/tutorials/source_en/advanced_use/images/side_infer_process.png deleted file mode 100644 index ee33ae4f1cb0153c27612cbe22480ad146641a88..0000000000000000000000000000000000000000 Binary files a/tutorials/source_en/advanced_use/images/side_infer_process.png and /dev/null differ diff --git a/tutorials/source_en/advanced_use/images/side_infer_process_en.png b/tutorials/source_en/advanced_use/images/side_infer_process_en.png new file mode 100644 index 0000000000000000000000000000000000000000..905f55f765ac2f74e3d1b86b4ca431b26d7da1c4 Binary files /dev/null and b/tutorials/source_en/advanced_use/images/side_infer_process_en.png differ diff --git a/tutorials/source_en/advanced_use/on_device_inference.md b/tutorials/source_en/advanced_use/on_device_inference.md index 4ad93afeb44e80221d0f8fabdac196079472b840..d38ad64e21c1b72a09630eda5d5e9e59e248776b 100644 --- a/tutorials/source_en/advanced_use/on_device_inference.md +++ b/tutorials/source_en/advanced_use/on_device_inference.md @@ -29,9 +29,10 @@ Mindspore Lite's framework consists of frontend, IR, backend, Lite, RT and micro - Lite RT: In the inference runtime, session provides the external interface, kernel registry is operator registry, scheduler is operator heterogeneous scheduler and executor is operator executor. Lite RT and shares with Micro the underlying infrastructure layers such as operator library, memory allocation, runtime thread pool and parallel primitives. - Micro: Code Gen generates .c files according to the model, and infrastructure such as the underlying operator library is shared with Lite RT. + ## Compilation Method -You need to compile the MindSpore Predict by yourself. This section describes how to perform cross compilation in the Ubuntu environment. +You need to compile the MindSpore Lite by yourself. This section describes how to perform cross compilation in the Ubuntu environment. The environment requirements are as follows: @@ -40,8 +41,8 @@ The environment requirements are as follows: - Hard disk space: 10 GB or above - System requirements - - System: Ubuntu = 18.04.02LTS (availability is checked) - - Kernel: 4.15.0-45-generic (availability is checked) + - System is limited on Linux + - Recommend system: Ubuntu = 18.04.02LTS - Software dependencies - [cmake](https://cmake.org/download/) >= 3.14.1 @@ -53,13 +54,9 @@ The environment requirements are as follows: - decorator - scipy - > `numpy`, `decorator` and `scipy` can be installed through `pip`. The reference command is as following. + > `numpy decorator scipy` can be installed through `pip`. The reference command is as: `pip3 install numpy==1.16 decorator scipy`. + - ```bash - pip3 install numpy==1.16 decorator scipy - ``` - - The compilation procedure is as follows: 1. Configure environment variables. @@ -75,18 +72,17 @@ The compilation procedure is as follows: git clone https://gitee.com/mindspore/mindspore.git ``` -3. Run the following command in the root directory of the source code to compile MindSpore Predict: -I indicates options for compiling MindSpore Predict and the parameter is the target platform architecture. Currently, only the Android arm64 platform is supported. +3. Run the following command in the root directory of the source code to compile MindSpore Lite. ```bash - sh build.sh -I arm64 + cd mindspore/lite + sh build.sh ``` 4. Obtain the compilation result. - Go to the `predict/output` directory of the source code to view the generated package. The package name is MSPredict-*Version number*-*Host platform*_*Device platform*.tar.gz, for example, MSPredict-0.1.0-linux_aarch64.tar.gz. The package contains the following directories: - - - include: MindSpore Predict header file. - - lib: MindSpore Predict dynamic library. + Go to the `lite/build` directory of the source code to view the generated documents. Then you can use various tools after changing directory. + ## Use of On-Device Inference @@ -169,164 +165,56 @@ if __name__ == '__main__': Use the `.ms` model file and image data as input to create a session and implement inference on the device. -![](./images/side_infer_process.png) +![](./images/side_infer_process_en.png) -Figure 2 On-device inference sequence diagram 1. Load the `.ms` model file to the memory buffer. The ReadFile function needs to be implemented by users, according to the [C++ tutorial](http://www.cplusplus.com/doc/tutorial/files/). ```cpp - // read model file - std::string modelPath = "./models/lenet/lenet.ms"; - size_t graphSize = 0; - - /* ReadFile() here is a dummy function */ - char *graphBuf = ReadFile(modelPath.c_str(), graphSize); + // Read Model File + std::string model_path = "./model.ms"; + ReadFile(model_path.c_str(), &model_size, buf); + + // Import Model + auto model = lite::Model::Import(content, size); + meta_graph.reset(); + content = nullptr; + auto context = new lite::Context; + context->cpuBindMode = lite::NO_BIND; + context->deviceCtx.type = lite::DT_CPU; + context->threadNum = 4; ``` -2. Call the CreateSession API to create a session. After the session is created, the model file in the memory buffer can be released. +2. Call the `CreateSession` API to get a session. ```cpp - // create session - Context ctx; - std::shared_ptr session = CreateSession(graphBuf, graphSize, ctx); - free(graphBuf); + // Create Session + auto session = session::LiteSession::CreateSession(context); + ASSERT_NE(nullptr, session); ``` -3. Read the input data for inference from the memory buffer and call the `SetData` API to set the input data to `input tensor`. +3. Call the `CompileGraph` API in previous `Session` and transport model. ```cpp - // load input buffer - size_t inputSize = 0; - std::string imagePath = "./data/input/lenet.bin"; - char *inputBuf = ReadFile(imagePath.c_str(), inputSize); - - //get input tensors - std::vector inputs = session->GetInput(); - //set input buffer - inputs[0]->SetData(inputBuf); + // Compile Graph + auto ret = session->CompileGraph(model.get()); + ASSERT_EQ(lite::RET_OK, ret); ``` - -4. Call the `Run` API in the `session` to perform inference. +4. Call the `GetInputs` API to get input `tensor`, then set graph information as `data`, `data` will be used in to perform model inference. ```cpp - // session run - int ret = session->Run(inputs); + auto inputs = session->GetInputs(); + ASSERT_EQ(inputs.size(), 1); + auto inTensor = inputs.front(); + ASSERT_NE(nullptr, inTensor); + (void)inTensor->MutableData(); ``` -5. Call the `GetAllOutput` API to obtain the output. - ```cpp - // get output - std::map> outputs = session->GetAllOutput(); - ``` - -6. Call the `Getdata` API to get the output data. +5. Call the `RunGraph` API in the `Session` to perform inference. ```cpp - // get output data - float *data = nullptr; - for (auto output : outputs) { - auto tensors = output.second; - for (auto tensor : tensors) { - data = (float *)(tensor->GetData()); - } - } + // Run Graph + ret = session->RunGraph(); + ASSERT_EQ(lite::RET_OK, ret); ``` -7. Release input and output tensors after the inference is complete. +6. Call the `GetOutputs` API to obtain the output. ```cpp - // free inputs and outputs - for (auto &input : inputs) { - delete input; - } - inputs.clear(); - for (auto &output : outputs) { - for (auto &outputTensor : output.second) { - delete outputTensor; - } - } - outputs.clear(); + // Get Outputs + auto outputs = session->GetOutputs(); ``` - -Select the LeNet network and set the inference input to `lenet.bin`. The complete sample code `lenet.cpp` is as follows: -> MindSpore Predict uses `FlatBuffers` to define models. The `FlatBuffers` header file is required for parsing models. Therefore, you need to configure the `FlatBuffers` header file. -> -> Method: Copy the `flatbuffers` folder in MindSpore root directory`/third_party/flatbuffers/include` to the directory at the same level as `session.h`. - -```cpp -#include -#include -#include "context.h" -#include "session.h" -#include "tensor.h" -#include "errorcode.h" - -using namespace mindspore::predict; - -int main() { - std::string modelPath = "./models/lenet/lenet.ms"; - std::string imagePath = "./data/input/lenet.bin"; - - // read model file - size_t graphSize = 0; - - /* ReadFile() here is a dummy function */ - char *graphBuf = ReadFile(modelPath.c_str(), graphSize); - if (graphBuf == nullptr) { - return -1; - } - - // create session - Context ctx; - auto session = CreateSession(graphBuf, graphSize, ctx); - if (session == nullptr) { - free(graphBuf); - return -1; - } - free(graphBuf); - - // load input buf - size_t inputSize = 0; - char *inputBuf = ReadFile(imagePath.c_str(), inputSize); - if (inputBuf == nullptr) { - return -1; - } - - auto inputs = session->GetInput(); - inputs[0]->SetData(inputBuf); - - // session run - auto ret = session->Run(inputs); - if (ret != RET_OK) { - printf("run failed, error: %d\n", ret); - for (auto &input : inputs) { - delete input; - } - return -1; - } - - // get output - auto outputs = session->GetAllOutput(); - - // get output data - float *data = nullptr; - for (auto output : outputs) { - auto tensors = output.second; - for (auto tensor : tensors) { - data = (float *)(tensor->GetData()); - //print the contents of the data - for (size_t i = 0; i < tensor->GetElementSize(); ++i) { - printf(" %f ", data[i]); - } - printf("\n"); - } - } - - // free inputs and outputs - for (auto &input : inputs) { - delete input; - } - inputs.clear(); - for (auto &output : outputs) { - for (auto &outputTensor : output.second) { - delete outputTensor; - } - } - outputs.clear(); - return 0; -} -``` + \ No newline at end of file diff --git a/tutorials/source_zh_cn/advanced_use/images/side_infer_process.png b/tutorials/source_zh_cn/advanced_use/images/side_infer_process.png index e4b599eb8af6ff927ce8e0441934029b11a9bc36..e1629ebe1637d98b26a02f3c0db41dced8779d42 100644 Binary files a/tutorials/source_zh_cn/advanced_use/images/side_infer_process.png and b/tutorials/source_zh_cn/advanced_use/images/side_infer_process.png differ diff --git a/tutorials/source_zh_cn/advanced_use/on_device_inference.md b/tutorials/source_zh_cn/advanced_use/on_device_inference.md index a43af5c431a44aead9cbed8be88d0de99bea54d1..e72508fcf4dafd45935d2e195a33b6e11d09da2a 100644 --- a/tutorials/source_zh_cn/advanced_use/on_device_inference.md +++ b/tutorials/source_zh_cn/advanced_use/on_device_inference.md @@ -41,8 +41,8 @@ MindSpore Lite的框架主要由Frontend、IR、Backend、Lite RT、Micro构成 - 硬盘空间10GB以上 - 系统要求 - - 系统：Ubuntu = 18.04.02LTS（验证可用） - - 内核：4.15.0-45-generic（验证可用） + - 系统环境仅支持Linux + - 推荐系统：Ubuntu = 18.04.02LTS - 软件依赖 - [cmake](https://cmake.org/download/) >= 3.14.1 @@ -54,18 +54,15 @@ MindSpore Lite的框架主要由Frontend、IR、Backend、Lite RT、Micro构成 - decorator - scipy - > `numpy`、 `decorator`和`scipy`可以通过`pip`安装，参考命令如下。 + > `numpy decorator scipy`可以通过`pip`安装，参考命令：`pip3 install numpy==1.16 decorator scipy`。 - ```bash - pip3 install numpy==1.16 decorator scipy - ``` 编译步骤如下： 1. 配置环境变量。 ```bash - export LLVM_PATH={$LLVM_PATH}/clang+llvm-8.0.0-x86_64-linux-gnu-ubuntu-16.04/bin/llvm-config #设定llvm路径 + export LLVM_PATH={$LLVM_PATH}/clang+llvm-8.0.0-x86_64-linux-gnu-ubuntu-18.04/bin/llvm-config #设定llvm路径 export ANDROID_NDK={$NDK_PATH}/android-ndk-r16b #设定ndk路径 ``` @@ -75,18 +72,16 @@ MindSpore Lite的框架主要由Frontend、IR、Backend、Lite RT、Micro构成 git clone https://gitee.com/mindspore/mindspore.git ``` -3. 在源码根目录下，执行如下命令编译MindSpore Predict。-I为编译MindSpore Predict的编译参数，-I的参数为目标端侧平台，目前仅支持安卓arm64平台。 +3. 在源码根目录下，执行如下命令编译MindSpore Lite。 ```bash - sh build.sh -I arm64 + cd mindspore/lite + sh build.sh ``` 4. 获取编译结果。 - 进入源码的`predict/output`目录，即可查看生成的压缩包，包名为MSPredict-*版本号*-*HOST平台*_*DEVICE平台*.tar.gz，例如：MSPredict-0.1.0-linux_aarch64.tar.gz。 该压缩包包含以下目录： - - - include：MindSpore Predict的头文件。 - - lib：MindSpore Predict的动态库。 + 进入源码的`lite/build`目录，可查看编译后生成的文件。进入相对应的文件夹下执行命令，就可以使用MindSpore Lite的多种功能。 ## 端侧推理使用 @@ -172,161 +167,56 @@ if __name__ == '__main__': ![](./images/side_infer_process.png) 图2：端侧推理时序图 -1. 加载`.ms`模型文件到内存缓冲区，ReadFile函数功能需要用户参考[C++教程](http://www.cplusplus.com/doc/tutorial/files/)自行实现。 - ```cpp - // read model file - std::string modelPath = "./models/lenet/lenet.ms"; - size_t graphSize = 0; - /* ReadFile() here is a dummy function */ - char *graphBuf = ReadFile(modelPath.c_str(), graphSize); +1. 读取MindSpore端侧模型文件信息。ReadFile函数功能需要用户参考[C++教程](http://www.cplusplus.com/doc/tutorial/files/)自行实现。 + ```cpp + // Read Model File + std::string model_path = "./model.ms"; + ReadFile(model_path.c_str(), &model_size, buf); + + // Import Model + auto model = lite::Model::Import(content, size); + meta_graph.reset(); + content = nullptr; + auto context = new lite::Context; + context->cpuBindMode = lite::NO_BIND; + context->deviceCtx.type = lite::DT_CPU; + context->threadNum = 4; ``` -2. 调用`CreateSession`接口创建`Session`，创建完成后可释放内存缓冲区中的模型文件。 +2. 调用`CreateSession`接口创建`Session`。 ```cpp - // create session - Context ctx; - std::shared_ptr session = CreateSession(graphBuf, graphSize, ctx); - free(graphBuf); + // Create Session + auto session = session::LiteSession::CreateSession(context); + ASSERT_NE(nullptr, session); ``` -3. 从内存缓冲区中读取推理的输入数据，调用`SetData`接口将输入数据设置到`input tensor`中。 +3. 调用`Session`中的`CompileGraph`方法，传入模型。 ```cpp - // load input buffer - size_t inputSize = 0; - std::string imagePath = "./data/input/lenet.bin"; - char *inputBuf = ReadFile(imagePath.c_str(), inputSize); - - //get input tensors - std::vector inputs = session->GetInput(); - //set input buffer - inputs[0]->SetData(inputBuf); + // Compile Graph + auto ret = session->CompileGraph(model.get()); + ASSERT_EQ(lite::RET_OK, ret); ``` - -4. 调用`Session`中的`Run`接口执行推理。 + +4. 调用`Session`中的`GetInputs`方法，获取输入`Tensor`，获取图片信息设置为`data`,`data`即为用于推理的输入数据。 ```cpp - // session run - int ret = session->Run(inputs); + auto inputs = session->GetInputs(); + ASSERT_EQ(inputs.size(), 1); + auto inTensor = inputs.front(); + ASSERT_NE(nullptr, inTensor); + (void)inTensor->MutableData(); ``` -5. 调用`GetAllOutput`接口获取输出。 +5. 调用`Session`中的`RunGraph`接口执行推理。 ```cpp - // get output - std::map> outputs = session->GetAllOutput(); + // Run Graph + ret = session->RunGraph(); + ASSERT_EQ(lite::RET_OK, ret); ``` - -6. 调用`Tensor`的`GetData`接口获取输出数据。 + +6. 调用`GetOutputs`接口获取输出。 ```cpp - // get output data - float *data = nullptr; - for (auto output : outputs) { - auto tensors = output.second; - for (auto tensor : tensors) { - data = (float *)(tensor->GetData()); - } - } + // Get Outputs + auto outputs = session->GetOutputs(); ``` -7. 推理结束释放`input tensor`和`output tensor`。 - ```cpp - // free inputs and outputs - for (auto &input : inputs) { - delete input; - } - inputs.clear(); - for (auto &output : outputs) { - for (auto &outputTensor : output.second) { - delete outputTensor; - } - } - outputs.clear(); - ``` - -选取LeNet网络，推理输入为“`lenet.bin`”，完整示例代码`lenet.cpp`如下。 -> MindSpore Predict使用`FlatBuffers`定义模型，解析模型需要使用到`FlatBuffers`头文件，因此用户需要自行配置`FlatBuffers`头文件。 -> -> 具体做法：将MindSpore根目录`/third_party/flatbuffers/include`下的`flatbuffers`文件夹拷贝到`session.h`的同级目录。 - -```cpp -#include -#include -#include "context.h" -#include "session.h" -#include "tensor.h" -#include "errorcode.h" - -using namespace mindspore::predict; - -int main() { - std::string modelPath = "./models/lenet/lenet.ms"; - std::string imagePath = "./data/input/lenet.bin"; - - // read model file - size_t graphSize = 0; - - /* ReadFile() here is a dummy function */ - char *graphBuf = ReadFile(modelPath.c_str(), graphSize); - if (graphBuf == nullptr) { - return -1; - } - - // create session - Context ctx; - auto session = CreateSession(graphBuf, graphSize, ctx); - if (session == nullptr) { - free(graphBuf); - return -1; - } - free(graphBuf); - - // load input buf - size_t inputSize = 0; - char *inputBuf = ReadFile(imagePath.c_str(), inputSize); - if (inputBuf == nullptr) { - return -1; - } - - auto inputs = session->GetInput(); - inputs[0]->SetData(inputBuf); - - // session run - auto ret = session->Run(inputs); - if (ret != RET_OK) { - printf("run failed, error: %d\n", ret); - for (auto &input : inputs) { - delete input; - } - return -1; - } - - // get output - auto outputs = session->GetAllOutput(); - - // get output data - float *data = nullptr; - for (auto output : outputs) { - auto tensors = output.second; - for (auto tensor : tensors) { - data = (float *)(tensor->GetData()); - //print the contents of the data - for (size_t i = 0; i < tensor->GetElementSize(); ++i) { - printf(" %f ", data[i]); - } - printf("\n"); - } - } - - // free inputs and outputs - for (auto &input : inputs) { - delete input; - } - inputs.clear(); - for (auto &output : outputs) { - for (auto &outputTensor : output.second) { - delete outputTensor; - } - } - outputs.clear(); - return 0; -} -```