From 24c0638bdeaf6b682f3c8c215f5dc1994a57ccd4 Mon Sep 17 00:00:00 2001 From: wang_shaocong Date: Fri, 4 Dec 2020 17:37:01 +0800 Subject: [PATCH] add readme files for image_segmentation demo. --- .../lite/image_segmentation/README.en.md | 330 +++++++++++++++++ .../lite/image_segmentation/README.md | 345 ++++++++++++++++++ 2 files changed, 675 insertions(+) create mode 100644 model_zoo/official/lite/image_segmentation/README.en.md create mode 100644 model_zoo/official/lite/image_segmentation/README.md diff --git a/model_zoo/official/lite/image_segmentation/README.en.md b/model_zoo/official/lite/image_segmentation/README.en.md new file mode 100644 index 0000000000..d069b244c7 --- /dev/null +++ b/model_zoo/official/lite/image_segmentation/README.en.md @@ -0,0 +1,330 @@ +## Demo of Image Segmentation + +The following describes how to use the MindSpore Lite C++ APIs (Android JNIs) and MindSpore Lite image segmentation models to perform on-device inference, classify the content captured by a device camera, and display the most possible segmentation result on the application's image preview screen. + +### Running Dependencies + +- Android Studio 3.2 or later (Android 4.0 or later is recommended.) +- Native development kit (NDK) 21.3 +- CMake 3.10.2 [CMake](https://cmake.org/download) +- Android software development kit (SDK) 26 or later +- JDK 1.8 or later + +### Building and Running + +1. Load the sample source code to Android Studio and install the corresponding SDK. (After the SDK version is specified, Android Studio automatically installs the SDK.) + + ![start_home](images/home.png) + + Start Android Studio, click `File > Settings > System Settings > Android SDK`, and select the corresponding SDK. As shown in the following figure, select an SDK and click `OK`. Android Studio automatically installs the SDK. + + ![start_sdk](images/sdk_management.png) + + If you have any Android Studio configuration problem when trying this demo, please refer to item 5 to resolve it. + +2. Connect to an Android device and runs the image segmentation application. + + Connect to the Android device through a USB cable for debugging. Click `Run 'app'` to run the sample project on your device. + + ![run_app](images/run_app.PNG) + + For details about how to connect the Android Studio to a device for debugging, see . + + The mobile phone needs to be turn on "USB debugging mode" before Android Studio can recognize the mobile phone. Huawei mobile phones generally turn on "USB debugging model" in Settings > system and update > developer Options > USB debugging. + +3. Continue the installation on the Android device. After the installation is complete, you can view the content captured by a camera and the inference result. + + ![result](images/app_result.jpg) + +4. The solutions of Android Studio configuration problems: + + | | Warning | Solution | + | ---- | ------------------------------------------------------------ | ------------------------------------------------------------ | + | 1 | Gradle sync failed: NDK not configured. | Specify the installed ndk directory in local.properties：ndk.dir={ndk的安装目录} | + | 2 | Requested NDK version did not match the version requested by ndk.dir | Manually download corresponding [NDK Version](https://developer.android.com/ndk/downloads)，and specify the sdk directory in Project Structure - Android NDK location.（You can refer to the figure below.） | + | 3 | This version of Android Studio cannot open this project, please retry with Android Studio or newer. | Update Android Studio Version in Tools - help - Checkout for Updates. | + | 4 | SSL peer shut down incorrectly | Run this demo again. | + + ![project_structure](images/project_structure.png) + +## Detailed Description of the Sample Program + +This image segmentation sample program on the Android device includes a Java layer and a JNI layer. At the Java layer, the Android Camera 2 API is used to enable a camera to obtain image frames and process images. At the JNI layer, the model inference process is completed in [Runtime](https://www.mindspore.cn/tutorial/lite/en/master/use/runtime.html). + +### Sample Program Structure + +```text +app +│ +├── src/main +│ ├── assets # resource files +| | └── deeplabv3.ms # model file +│ | +│ ├── cpp # main logic encapsulation classes for model loading and prediction +| | | +| | ├── MindSporeNetnative.cpp # JNI methods related to MindSpore calling +│ | └── MindSporeNetnative.h # header file +│ | +│ ├── java # application code at the Java layer +│ │ └── com.mindspore.himindsporedemo +│ │ ├── gallery.classify # implementation related to image processing and MindSpore JNI calling +│ │ │ └── ... +│ │ └── widget # implementation related to camera enabling and drawing +│ │ └── ... +│ │ +│ ├── res # resource files related to Android +│ └── AndroidManifest.xml # Android configuration file +│ +├── CMakeList.txt # CMake compilation entry file +│ +├── build.gradle # Other Android configuration file +├── download.gradle # MindSpore version download +└── ... +``` + +### Configuring MindSpore Lite Dependencies + +When MindSpore C++ APIs are called at the Android JNI layer, related library files are required. You can use MindSpore Lite [source code compilation](https://www.mindspore.cn/tutorial/lite/en/master/use/build.html) to generate the MindSpore Lite version. In this case, you need to use the compile command of generate with image preprocessing module. + +In this example, the build process automatically downloads the `mindspore-lite-1.0.1-runtime-arm64-cpu` by the `app/download.gradle` file and saves in the `app/src/main/cpp` directory. + +Note: if the automatic download fails, please manually download the relevant library files and put them in the corresponding location. + +mindspore-lite-1.0.1-runtime-arm64-cpu.tar.gz [Download link](https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.1/lite/android_aarch64/mindspore-lite-1.0.1-runtime-arm64-cpu.tar.gz) + +```text +android{ + defaultConfig{ + externalNativeBuild{ + cmake{ + arguments "-DANDROID_STL=c++_shared" + } + } + + ndk{ + abiFilters'armeabi-v7a', 'arm64-v8a' + } + } +} +``` + +Create a link to the `.so` library file in the `app/CMakeLists.txt` file: + +```text +# ============== Set MindSpore Dependencies. ============= +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/third_party/flatbuffers/include) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/include) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/include/ir/dtype) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/include/schema) + +add_library(mindspore-lite SHARED IMPORTED ) +add_library(minddata-lite SHARED IMPORTED ) + +set_target_properties(mindspore-lite PROPERTIES IMPORTED_LOCATION + ${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/lib/libmindspore-lite.so) +set_target_properties(minddata-lite PROPERTIES IMPORTED_LOCATION + ${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/lib/libminddata-lite.so) +# --------------- MindSpore Lite set End. -------------------- + +# Link target library. +target_link_libraries( + ... + # --- mindspore --- + minddata-lite + mindspore-lite + ... +) +``` + +### Downloading and Deploying a Model File + +In this example, the download.gradle File configuration auto download `deeplabv3.ms`and placed in the 'app/libs/arm64-v8a' directory. + +Note: if the automatic download fails, please manually download the relevant library files and put them in the corresponding location. + +deeplabv3.ms [deeplabv3.ms]( https://download.mindspore.cn/model_zoo/official/lite/deeplabv3_openimage_lite/deeplabv3.ms) + +### Compiling On-Device Inference Code + +Call MindSpore Lite Java APIs to implement on-device inference. + +The inference code process is as follows. For details about the complete code, see `src/java/TrackingMobile.java`. + +1. Load the MindSpore Lite model file and build the context, session, and computational graph for inference. + + - Load a model file. Import and configure the context for model inference. + + ```Java + // Create context and load the .ms model named 'IMAGESEGMENTATIONMODEL' + model = new Model(); + if (!model.loadModel(Context, IMAGESEGMENTATIONMODEL)) { + Log.e(TAG, "Load Model failed"); + return; + } + ``` + + - Create a session. + + ```Java + // Create and init config. + msConfig = new MSConfig(); + if (!msConfig.init(DeviceType.DT_CPU, 2, CpuBindMode.MID_CPU)) { + Log.e(TAG, "Init context failed"); + return; + } + + // Create the MindSpore lite session. + session = new LiteSession(); + if (!session.init(msConfig)) { + Log.e(TAG, "Create session failed"); + msConfig.free(); + return; + } + msConfig.free(); + ``` + + - Compile graph for inference. + + ```Java + if (!session.compileGraph(model)) { + Log.e(TAG, "Compile graph failed"); + model.freeBuffer(); + return; + } + // Note: when use model.freeBuffer(), the model can not be complile graph again. + model.freeBuffer(); + ``` + +2. Convert the input image into the Tensor format of the MindSpore model. + + ```Java + List inputs = session.getInputs(); + if (inputs.size() != 1) { + Log.e(TAG, "inputs.size() != 1"); + return null; + } + + // `bitmap` is the picture used to infer. + float resource_height = bitmap.getHeight(); + float resource_weight = bitmap.getWidth(); + ByteBuffer contentArray = bitmapToByteBuffer(bitmap, imageSize, imageSize, IMAGE_MEAN, IMAGE_STD); + + MSTensor inTensor = inputs.get(0); + inTensor.setData(contentArray); + ``` + +3. Perform inference on the input tensor based on the model, obtain the output tensor, and perform post-processing. + + - Perform graph execution and on-device inference. + + ```Java + // After the model and image tensor data is loaded, run inference. + if (!session.runGraph()) { + Log.e(TAG, "Run graph failed"); + return null; + } + ``` + + - Obtain the output data. + + ```Java + // Get output tensor values, the model only outputs one tensor. + List tensorNames = session.getOutputTensorNames(); + MSTensor output = session.getOutputByTensorName(tensorNames.front()); + if (output == null) { + Log.e(TAG, "Can not find output " + tensorName); + return null; + } + ``` + + - Perform post-processing of the output data. + + ```Java + // Show output as pictures. + float[] results = output.getFloatData(); + + ByteBuffer bytebuffer_results = floatArrayToByteArray(results); + + Bitmap dstBitmap = convertBytebufferMaskToBitmap(bytebuffer_results, imageSize, imageSize, bitmap, dstBitmap, segmentColors); + dstBitmap = scaleBitmapAndKeepRatio(dstBitmap, (int) resource_height, (int) resource_weight); + ``` + +4. The process of image and output data can refer to methods showing bellow. + + ```Java + Bitmap scaleBitmapAndKeepRatio(Bitmap targetBmp, int reqHeightInPixels, int reqWidthInPixels) { + if (targetBmp.getHeight() == reqHeightInPixels && targetBmp.getWidth() == reqWidthInPixels) { + return targetBmp; + } + + Matrix matrix = new Matrix(); + matrix.setRectToRect(new RectF(0f, 0f, targetBmp.getWidth(), targetBmp.getHeight()), + new RectF(0f, 0f, reqWidthInPixels, reqHeightInPixels), Matrix.ScaleToFit.FILL; + + return Bitmap.createBitmap(targetBmp, 0, 0, targetBmp.getWidth(), targetBmp.getHeight(), matrix, true); + } + + ByteBuffer bitmapToByteBuffer(Bitmap bitmapIn, int width, int height, float mean, float std) { + Bitmap bitmap = scaleBitmapAndKeepRatio(bitmapIn, width, height); + ByteBuffer inputImage = ByteBuffer.allocateDirect(1 * width * height * 3 * 4); + inputImage.order(ByteOrder.nativeOrder()); + inputImage.rewind(); + int[] intValues = new int[width * height]; + bitmap.getPixels(intValues, 0, width, 0, 0, width, height); + int pixel = 0; + for (int y = 0; y < height; y++) { + for (int x = 0; x < width; x++) { + int value = intValues[pixel++]; + inputImage.putFloat(((float) (value >> 16 & 255) - mean) / std); + inputImage.putFloat(((float) (value >> 8 & 255) - mean) / std); + inputImage.putFloat(((float) (value & 255) - mean) / std); + } + } + inputImage.rewind(); + return inputImage; + } + + ByteBuffer floatArrayToByteArray(float[] floats) { + ByteBuffer buffer = ByteBuffer.allocate(4 * floats.length); + FloatBuffer floatBuffer = buffer.asFloatBuffer(); + floatBuffer.put(floats); + return buffer; + } + + Bitmap convertBytebufferMaskToBitmap(ByteBuffer inputBuffer, int imageWidth, int imageHeight, Bitmap backgroundImage, int[] colors) { + Bitmap.Config conf = Bitmap.Config.ARGB_8888; + Bitmap dstBitmap = Bitmap.createBitmap(imageWidth, imageHeight, conf); + Bitmap scaledBackgroundImage = scaleBitmapAndKeepRatio(backgroundImage, imageWidth, imageHeight); + int[][] mSegmentBits = new int[imageWidth][imageHeight]; + inputBuffer.rewind(); + for (int y = 0; y < imageHeight; y++) { + for (int x = 0; x < imageWidth; x++) { + float maxVal = 0f; + mSegmentBits[x][y] = 0; + // NUM_CLASSES is the number of labels, the value here is 21. + for (int i = 0; i < NUM_CLASSES; i++) { + float value = inputBuffer.getFloat((y * imageWidth * NUM_CLASSES + x * NUM_CLASSES + i) * 4); + if (i == 0 || value > maxVal) { + maxVal = value; + // Check wether a pixel belongs to a person whose label is 15. + if (i == 15) { + mSegmentBits[x][y] = i; + } else { + mSegmentBits[x][y] = 0; + } + } + } + itemsFound.add(mSegmentBits[x][y]); + + int newPixelColor = ColorUtils.compositeColors( + colors[mSegmentBits[x][y] == 0 ? 0 : 1], + scaledBackgroundImage.getPixel(x, y) + ); + dstBitmap.setPixel(x, y, mSegmentBits[x][y] == 0 ? colors[0] : scaledBackgroundImage.getPixel(x, y)); + } + } + return dstBitmap; + } + ``` diff --git a/model_zoo/official/lite/image_segmentation/README.md b/model_zoo/official/lite/image_segmentation/README.md new file mode 100644 index 0000000000..dd6dd97431 --- /dev/null +++ b/model_zoo/official/lite/image_segmentation/README.md @@ -0,0 +1,345 @@ +## MindSpore Lite 端侧图像分割demo（Android） + +本示例程序演示了如何在端侧利用MindSpore Lite C++ API（Android JNI）以及MindSpore Lite 图像分割模型完成端侧推理，实现对设备摄像头捕获的内容进行分割，并在App图像预览界面中显示出最可能的分割结果。 + +### 运行依赖 + +- Android Studio >= 3.2 (推荐4.0以上版本) +- NDK 21.3 +- CMake 3.10.2 [CMake](https://cmake.org/download) +- Android SDK >= 26 +- JDK >= 1.8 + +### 构建与运行 + +1. 在Android Studio中加载本示例源码，并安装相应的SDK（指定SDK版本后，由Android Studio自动安装）。 + + ![start_home](images/home.png) + + 启动Android Studio后，点击`File->Settings->System Settings->Android SDK`，勾选相应的SDK。如下图所示，勾选后，点击`OK`，Android Studio即可自动安装SDK。 + + ![start_sdk](images/sdk_management.png) + + 使用过程中若出现Android Studio配置问题，可参考第5项解决。 + +2. 连接Android设备，运行图像分割应用程序。 + + 通过USB连接Android设备调试，点击`Run 'app'`即可在您的设备上运行本示例项目。 + + > 编译过程中Android Studio会自动下载MindSpore Lite、模型文件等相关依赖项，编译过程需做耐心等待。 + + ![run_app](images/run_app.PNG) + + Android Studio连接设备调试操作，可参考。 + + 手机需开启“USB调试模式”，Android Studio 才能识别到手机。 华为手机一般在设置->系统和更新->开发人员选项->USB调试中开始“USB调试模型”。 + +3. 在Android设备上，点击“继续安装”，安装完即可查看到设备摄像头捕获的内容和推理结果。 + + ![install](images/install.jpg) + + 如下图所示，识别出的概率最高的物体是植物。 + + ![result](images/app_result.jpg) + +4. Android Studio 配置问题解决方案可参考下表： + + | | 报错 | 解决方案 | + | ---- | ------------------------------------------------------------ | ------------------------------------------------------------ | + | 1 | Gradle sync failed: NDK not configured. | 在local.properties中指定安装的ndk目录：ndk.dir={ndk的安装目录} | + | 2 | Requested NDK version did not match the version requested by ndk.dir | 可手动下载相应的[NDK版本](https://developer.android.com/ndk/downloads?hl=zh-cn)，并在Project Structure - Android NDK location设置中指定SDK的位置（可参考下图完成） | + | 3 | This version of Android Studio cannot open this project, please retry with Android Studio or newer. | 在工具栏-help-Checkout for Updates中更新版本 | + | 4 | SSL peer shut down incorrectly | 重新构建 | + + ![project_structure](images/project_structure.png) + +## 示例程序详细说明 + +本端侧图像分割Android示例程序分为JAVA层和JNI层，其中，JAVA层主要通过Android Camera 2 API实现摄像头获取图像帧，以及相应的图像处理等功能；JNI层完成模型推理的过程。 + +> 此处详细说明示例程序的JNI层实现，JAVA层运用Android Camera 2 API实现开启设备摄像头以及图像帧处理等功能，需读者具备一定的Android开发基础知识。 + +### 示例程序结构 + +```text +app +├── src/main +│ ├── assets # 资源文件 +| | └── deeplabv3.ms # 存放模型文件 +│ | +│ ├── cpp # 模型加载和预测主要逻辑封装类 +| | ├── .. +| | ├── mindspore_lite_x.x.x-minddata-arm64-cpu #MindSpore Lite版本 +| | ├── MindSporeNetnative.cpp # MindSpore调用相关的JNI方法 +│ | └── MindSporeNetnative.h # 头文件 +| | └── MsNetWork.cpp # MindSpre接口封装 +│ | +│ ├── java # java层应用代码 +│ │ └── com.mindspore.himindsporedemo +│ │ ├── gallery.classify # 图像处理及MindSpore JNI调用相关实现 +│ │ │ └── ... +│ │ └── widget # 开启摄像头及绘制相关实现 +│ │ └── ... +│ │ +│ ├── res # 存放Android相关的资源文件 +│ └── AndroidManifest.xml # Android配置文件 +│ +├── CMakeList.txt # cmake编译入口文件 +│ +├── build.gradle # 其他Android配置文件 +├── download.gradle # 工程依赖文件下载 +└── ... +``` + +### 配置MindSpore Lite依赖项 + +Android JNI层调用MindSpore C++ API时，需要相关库文件支持。可通过MindSpore Lite[源码编译](https://www.mindspore.cn/tutorial/lite/zh-CN/master/use/build.html)生成`mindspore-lite-{version}-minddata-{os}-{device}.tar.gz`库文件包并解压缩（包含`libmindspore-lite.so`库文件和相关头文件），在本例中需使用生成带图像预处理模块的编译命令。 + +> version：输出件版本号，与所编译的分支代码对应的版本一致。 +> +> device：当前分为cpu（内置CPU算子）和gpu（内置CPU和GPU算子）。 +> +> os：输出件应部署的操作系统。 + +本示例中，build过程由download.gradle文件自动下载MindSpore Lite 版本文件，并放置在`app/src/main/cpp/`目录下。 + +> 若自动下载失败，请手动下载相关库文件，解压并放在对应位置： + + mindspore-lite-1.0.1-runtime-arm64-cpu.tar.gz [下载链接](https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.1/lite/android_aarch64/mindspore-lite-1.0.1-runtime-arm64-cpu.tar.gz) + +在app的`build.gradle`文件中配置CMake编译支持，以及`arm64-v8a`的编译支持，如下所示： + +```text +android{ + defaultConfig{ + externalNativeBuild{ + cmake{ + arguments "-DANDROID_STL=c++_shared" + } + } + + ndk{ + abiFilters 'arm64-v8a' + } + } +} +``` + +在`app/CMakeLists.txt`文件中建立`.so`库文件链接，如下所示。 + +```text +# ============== Set MindSpore Dependencies. ============= +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/third_party/flatbuffers/include) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/include) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/include/ir/dtype) +include_directories(${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/include/schema) + +add_library(mindspore-lite SHARED IMPORTED ) +add_library(minddata-lite SHARED IMPORTED ) + +set_target_properties(mindspore-lite PROPERTIES IMPORTED_LOCATION + ${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/lib/libmindspore-lite.so) +set_target_properties(minddata-lite PROPERTIES IMPORTED_LOCATION + ${CMAKE_SOURCE_DIR}/src/main/cpp/${MINDSPORELITE_VERSION}/lib/libminddata-lite.so) +# --------------- MindSpore Lite set End. -------------------- + +# Link target library. +target_link_libraries( + ... + # --- mindspore --- + minddata-lite + mindspore-lite + ... +) +``` + +### 下载及部署模型文件 + +从MindSpore Model Hub中下载模型文件，本示例程序中使用的终端图像分割模型文件为`deeplabv3.ms`，同样通过download.gradle脚本在APP构建时自动下载，并放置在`app/src/main/assets`工程目录下。 + +> 若下载失败请手动下载模型文件，deeplabv3.ms [下载链接](https://download.mindspore.cn/model_zoo/official/lite/deeplabv3_openimage_lite/deeplabv3.ms)。 + +### 编写端侧推理代码 + +调用MindSpore Lite Java API实现端测推理。 + +推理代码流程如下，完整代码请参见`src/java/TrackingMobile.java`。 + +1. 加载MindSpore Lite模型文件，构建上下文、会话以及用于推理的计算图。 + + - 加载模型文件：创建并配置用于模型推理的上下文 + + ```Java + // Create context and load the .ms model named 'IMAGESEGMENTATIONMODEL' + model = new Model(); + if (!model.loadModel(Context, IMAGESEGMENTATIONMODEL)) { + Log.e(TAG, "Load Model failed"); + return; + } + ``` + + - 创建会话 + + ```Java + // Create and init config. + msConfig = new MSConfig(); + if (!msConfig.init(DeviceType.DT_CPU, 2, CpuBindMode.MID_CPU)) { + Log.e(TAG, "Init context failed"); + return; + } + + // Create the MindSpore lite session. + session = new LiteSession(); + if (!session.init(msConfig)) { + Log.e(TAG, "Create session failed"); + msConfig.free(); + return; + } + msConfig.free(); + ``` + + - 构建计算图 + + ```Java + if (!session.compileGraph(model)) { + Log.e(TAG, "Compile graph failed"); + model.freeBuffer(); + return; + } + // Note: when use model.freeBuffer(), the model can not be complile graph again. + model.freeBuffer(); + ``` + +2. 将输入图片转换为传入MindSpore模型的Tensor格式。 + + ```Java + List inputs = session.getInputs(); + if (inputs.size() != 1) { + Log.e(TAG, "inputs.size() != 1"); + return null; + } + + // `bitmap` is the picture used to infer. + float resource_height = bitmap.getHeight(); + float resource_weight = bitmap.getWidth(); + ByteBuffer contentArray = bitmapToByteBuffer(bitmap, imageSize, imageSize, IMAGE_MEAN, IMAGE_STD); + + MSTensor inTensor = inputs.get(0); + inTensor.setData(contentArray); + ``` + +3. 对输入Tensor按照模型进行推理，获取输出Tensor，并进行后处理。 + + - 图执行，端侧推理。 + + ```Java + // After the model and image tensor data is loaded, run inference. + if (!session.runGraph()) { + Log.e(TAG, "Run graph failed"); + return null; + } + ``` + + - 获取输出数据。 + + ```Java + // Get output tensor values, the model only outputs one tensor. + List tensorNames = session.getOutputTensorNames(); + MSTensor output = session.getOutputByTensorName(tensorNames.front()); + if (output == null) { + Log.e(TAG, "Can not find output " + tensorName); + return null; + } + ``` + + - 输出数据的后续处理。 + + ```Java + // Show output as pictures. + float[] results = output.getFloatData(); + + ByteBuffer bytebuffer_results = floatArrayToByteArray(results); + + Bitmap dstBitmap = convertBytebufferMaskToBitmap(bytebuffer_results, imageSize, imageSize, bitmap, dstBitmap, segmentColors); + dstBitmap = scaleBitmapAndKeepRatio(dstBitmap, (int) resource_height, (int) resource_weight); + ``` + +4. 图片处理及输出数据后处理请参考如下代码。 + + ```Java + Bitmap scaleBitmapAndKeepRatio(Bitmap targetBmp, int reqHeightInPixels, int reqWidthInPixels) { + if (targetBmp.getHeight() == reqHeightInPixels && targetBmp.getWidth() == reqWidthInPixels) { + return targetBmp; + } + + Matrix matrix = new Matrix(); + matrix.setRectToRect(new RectF(0f, 0f, targetBmp.getWidth(), targetBmp.getHeight()), + new RectF(0f, 0f, reqWidthInPixels, reqHeightInPixels), Matrix.ScaleToFit.FILL; + + return Bitmap.createBitmap(targetBmp, 0, 0, targetBmp.getWidth(), targetBmp.getHeight(), matrix, true); + } + + ByteBuffer bitmapToByteBuffer(Bitmap bitmapIn, int width, int height, float mean, float std) { + Bitmap bitmap = scaleBitmapAndKeepRatio(bitmapIn, width, height); + ByteBuffer inputImage = ByteBuffer.allocateDirect(1 * width * height * 3 * 4); + inputImage.order(ByteOrder.nativeOrder()); + inputImage.rewind(); + int[] intValues = new int[width * height]; + bitmap.getPixels(intValues, 0, width, 0, 0, width, height); + int pixel = 0; + for (int y = 0; y < height; y++) { + for (int x = 0; x < width; x++) { + int value = intValues[pixel++]; + inputImage.putFloat(((float) (value >> 16 & 255) - mean) / std); + inputImage.putFloat(((float) (value >> 8 & 255) - mean) / std); + inputImage.putFloat(((float) (value & 255) - mean) / std); + } + } + inputImage.rewind(); + return inputImage; + } + + ByteBuffer floatArrayToByteArray(float[] floats) { + ByteBuffer buffer = ByteBuffer.allocate(4 * floats.length); + FloatBuffer floatBuffer = buffer.asFloatBuffer(); + floatBuffer.put(floats); + return buffer; + } + + Bitmap convertBytebufferMaskToBitmap(ByteBuffer inputBuffer, int imageWidth, int imageHeight, Bitmap backgroundImage, int[] colors) { + Bitmap.Config conf = Bitmap.Config.ARGB_8888; + Bitmap dstBitmap = Bitmap.createBitmap(imageWidth, imageHeight, conf); + Bitmap scaledBackgroundImage = scaleBitmapAndKeepRatio(backgroundImage, imageWidth, imageHeight); + int[][] mSegmentBits = new int[imageWidth][imageHeight]; + inputBuffer.rewind(); + for (int y = 0; y < imageHeight; y++) { + for (int x = 0; x < imageWidth; x++) { + float maxVal = 0f; + mSegmentBits[x][y] = 0; + // NUM_CLASSES is the number of labels, the value here is 21. + for (int i = 0; i < NUM_CLASSES; i++) { + float value = inputBuffer.getFloat((y * imageWidth * NUM_CLASSES + x * NUM_CLASSES + i) * 4); + if (i == 0 || value > maxVal) { + maxVal = value; + // Check wether a pixel belongs to a person whose label is 15. + if (i == 15) { + mSegmentBits[x][y] = i; + } else { + mSegmentBits[x][y] = 0; + } + } + } + itemsFound.add(mSegmentBits[x][y]); + + int newPixelColor = ColorUtils.compositeColors( + colors[mSegmentBits[x][y] == 0 ? 0 : 1], + scaledBackgroundImage.getPixel(x, y) + ); + dstBitmap.setPixel(x, y, mSegmentBits[x][y] == 0 ? colors[0] : scaledBackgroundImage.getPixel(x, y)); + } + } + return dstBitmap; + } + ```