首页 > 其他分享 >【SDK案例系列 05】基于 MindX SDK + Pytorch MobileNetV2的目标分类

【SDK案例系列 05】基于 MindX SDK + Pytorch MobileNetV2的目标分类

时间:2023-01-06 18:48:09浏览次数:77  
标签:MindX mobilenet 05 -- mxpi sh root SDK

源码下载:

https://gitee.com/ai_samples/atlas_mindxsdk_samples/blob/master/contrib/cv/classification/image_mobilenetv2

快速运行攻略(MindX SDK环境已经部署完毕情况下):

1、获取模型文件

(1)MobilenetV2_for_PyTorch_1.2.onnx文件

https://gitee.com/ai_samples/pytorch_models/tree/master/cv/classification/mobilenet

存放到 image_mobilenetv2/data/models/mobilenet 目录下

2、模型文件转换

(1)image_mobilenetv2/data/models/mobilenet目录下执行模型转换,根据芯片类型,执行atc_310.sh 或 atc_310P3.sh

bash atc_310.sh
bash atc_310P3.sh

3、修改run_cpp.sh & run_python.sh中MX_SDK_HOME为MindX SDK安装目录

export MX_SDK_HOME=/usr/local/sdk_home/mxVision

4、执行run_cpp.sh 或者 run_python.sh

bash run_cpp.sh
bash run_python.sh

一、安装昇腾驱动

先安装昇腾驱动,昇腾驱动请参考各个产品安装手册,安装完成后npu-smi info 显示安装成功

[root@localhost ~]#
[root@localhost ~]# npu-smi info
+-------------------------------------------------------------------------------------------------+
| npu-smi 22.0.2                   Version: 22.0.2                                                |
+------------------+--------------+---------------------------------------------------------------+
| NPU    Name      | Health       | Power(W)             Temp(C)           Hugepages-Usage(page)  |
| Chip   Device    | Bus-Id       | AICore(%)            Memory-Usage(MB)                         |
+==================+==============+===============================================================+
| 1      310       | OK           | 12.8                 45                0   / 0                |
| 0      0         | 0000:05:00.0 | 0                    2621  / 8192                             |
+==================+==============+===============================================================+

二、安装MindX SDK > mxVision

(1)MindX SDK需要通过官网获取。

(2)mxVision说明手册:

https://www.hiascend.com/document/detail/zh/mind-sdk/30rc3/quickstart/visionquickstart/visionquickstart_0000.html

(3)安装MindX SDK

./Ascend-mindxsdk-mxvision_3.0.RC2_linux-aarch64.run --install --install-path=/usr/local/sdk_home

--install-path为指定安装的路径

(4)安装成功后会提示如下信息

Installing collected packages:mindx
Successfully installed mindx-3.0.RC2

(5)安装成功后在对应目录下查看,能看到mxVision

[root@localhost sdk_home]#
[root@localhost sdk_home]# pwd
/usr/local/sdk_home
[root@localhost sdk_home]# ls
mxVision mxVision-3.0.RC2
[root@localhost sdk_home]#
[root@localhost sdk_home]#

(6)MindX SDK使用中需要用到OSD功能,安装后需要执行以下命令,生成om文件

bash /usr/local/sdk_home/mxVision/operators/opencvosd/generate_osd_om.sh

执行成功后,显示如下效果

[root@localhost ~]# bash /usr/local/sdk_home/mxVision/operators/opencvosd/generate_osd_om.sh
ASCEND_HOME is set to /usr/local/Ascend by user
Set ASCEND_VERSION to the default value:ascend-toolkit/latest
ATC start working now,please wait for a moment.
ATC run success, welcome to the next use.

The model has been successfully converted to om,please get it under /usr/local/sdk_home/mxVision/operators/opencvosd.
[root@localhost ~]# 

(9)安装完MindX SDK后,需要配置环境变量

.bashrc文件添加以下环境变量

# 安装mxVision时配置
. /usr/local/sdk_home/mxVision/set_env.sh

用户也可以通过修改~/.bashrc文件方式设置永久环境变量,操作如下:

a) 以运行用户在任意目录下执行vi ~/.bashrc命令,打开.bashrc文件,在文件最后一行后面添加上述内容。
b) 执行:wq!命令保存文件并退出。
c) 执行source ~/.bashrc命令使其立即生效。

三、ATC模型转换

1、把训练好的mobilenetv2.pth模型转MobilenetV2_for_PyTorch_1.2.onnx后,放在image_mobilenetv2/data/models/mobilenet目录下

获取路径:

https://gitee.com/ai_samples/pytorch_models/tree/master/cv/classification/mobilenet

[root@localhost mobilenet]#
[root@localhost mobilenet]# ls
aipp_mobilenet_rgb.config  atc_310.sh  atc_310P3.sh  imagenet1000_clsidx_to_labels.names  mobilenet.cfg  MobilenetV2_for_PyTorch_1.2.onnx
[root@localhost mobilenet]# 

2、执行模型转换命令

Ascend310芯片模型转换命令如下:

atc \
    --mode=0 \
    --framework=5 \
    --model=./MobilenetV2_for_PyTorch_1.2.onnx \
    --output=./mobilenet \
    --input_format=NCHW \
    --input_shape="actual_input_1:1,3,336,336" \
    --enable_small_channel=1 \
    --log=error \
    --soc_version=Ascend310 \
    --insert_op_conf=aipp_mobilenet_rgb.config

Ascend310P3芯片模型转换命令如下:

atc \
    --mode=0 \
    --framework=5 \
    --model=./MobilenetV2_for_PyTorch_1.2.onnx \
    --output=./mobilenet \
    --input_format=NCHW \
    --input_shape="actual_input_1:1,3,336,336" \
    --enable_small_channel=1 \
    --log=error \
    --soc_version=Ascend310P3 \
    --insert_op_conf=aipp_mobilenet_rgb.config

参数说明:

--model:待转换的ONNX模型。

--framework:5代表ONNX模型。

--output:输出的om模型。

--input_format:输入数据的格式。

actual_input_1:取值根据实际使用场景确定。

--input_shape:输入数据的shape。

--enable_small_channel=1:对于mobilenet等视觉模型四维数据卷积算子的特殊优化,可以提升性能,其他模型可能导致性能下降,不建议开启。

--insert_op_conf=./aipp_mobilenet_rgb.config:AIPP插入节点,通过config文件配置算子信息,功能包括图片色域转换、裁剪、归一化,主要用于处理原图输入数据,常与DVPP配合使用,详见下文数据预处理。

详细ATC命令转换学习请参考:

https://support.huawei.com/enterprise/zh/doc/EDOC1100234054?idPath=23710424|251366513|22892968|251168373

3、模型转换后,会在目录下生成mobilenet.om

[root@localhost mobilenet]#
[root@localhost mobilenet]# ls
aipp_mobilenet_rgb.config  atc_310.sh  atc_310P3.sh  imagenet1000_clsidx_to_labels.names  mobilenet.cfg  mobilenet.om  MobilenetV2_for_PyTorch_1.2.onnx
[root@localhost mobilenet]# 

四、使用image_mobilenetv2

1、修改run_cpp.sh & run_python.sh中MX_SDK_HOME为MindX SDK安装目录

export MX_SDK_HOME=/usr/local/sdk_home/mxVision

2、执行run_cpp.sh 或者 run_python.sh

bash run_cpp.sh
bash run_python.sh

3、目标分类结果与test.jpg一致

目标分类结果:beagle

五、image_mobilenetv2详解

1、技术流程图

在这里插入图片描述

视频解码:调用OPENCV解码能力,转换为 YUV 格式图像数据。

图像缩放:调用OPENCV,将图像缩放到一定尺寸大小。

目标分类:MobileNetV2模型针对图像进行目标分类。

模型后处理:针对推理结果进行后处理文字转换。

数据序列化:将stream结果组装成json字符串输出。

2、pipeline详解

{
    "classification": {
        "stream_config": {  ##设置业务流在哪个芯片上处理
            "deviceId": "0"
        },
        "mxpi_imagedecoder0": {  ##图像解码(OpenCV方式)
            "props": {
                 "handleMethod": "opencv"
            },
            "factory": "mxpi_imagedecoder",
            "next": "mxpi_imageresize0"
        },
        "mxpi_imageresize0": {  ##图像缩放(OpenCV方式)
            "props": {
                "handleMethod": "opencv",
                "resizeType": "Resizer_Stretch",
                "resizeHeight": "336",
                "resizeWidth": "336"
            },
            "factory": "mxpi_imageresize",
            "next": "mxpi_tensorinfer0"
        },
        "mxpi_tensorinfer0": {  ##模型推理
            "props": {
                "dataSource": "mxpi_imageresize0",
                "modelPath": "data/models/mobilenet/mobilenet.om",  ##模型路径
                "waitingTime": "2000",
                "outputDeviceId": "-1"
            },
            "factory": "mxpi_tensorinfer",
            "next": "mxpi_classpostprocessor0"
        },
        "mxpi_classpostprocessor0": {  ##模型后处理
            "props": {
                "dataSource": "mxpi_tensorinfer0",
                "postProcessConfigPath": "data/models/mobilenet/mobilenet.cfg",
                "labelPath": "data/models/mobilenet/imagenet1000_clsidx_to_labels.names",
                "postProcessLibPath": "libresnet50postprocess.so"
            },
            "factory": "mxpi_classpostprocessor",
            "next": "mxpi_dataserialize0"
        },
        "mxpi_dataserialize0": {  ##数据序列化
            "props": {
                "outputDataKeys": "mxpi_classpostprocessor0"
            },
            "factory": "mxpi_dataserialize",
            "next": "appsink0"
        },
        "appsrc1": {
            "props": {
                "blocksize": "409600"
            },
            "factory": "appsrc",
            "next": "mxpi_imagedecoder0"
        },
        "appsink0": {  ##输出推理结果
            "props": {
                "blocksize": "4096000"
            },
            "factory": "appsink"
        }
    }
}

3、C++源码详解

int main(int argc, char* argv[])
{
    // 读取pipeline配置文件
    std::string pipelineConfigPath = "data/pipeline/Sample.pipeline";
    std::string pipelineConfig = ReadPipelineConfig(pipelineConfigPath);
    if (pipelineConfig == "") {
        LogError << "Read pipeline failed.";
        return APP_ERR_COMM_INIT_FAIL;
    }
    // 初始化 Stream manager 资源
    MxStream::MxStreamManager mxStreamManager;
    APP_ERROR ret = mxStreamManager.InitManager();
    if (ret != APP_ERR_OK) {
        LogError << GetError(ret) << "Failed to init Stream manager.";
        return ret;
    }
    // 根据指定的pipeline配置创建Stream
    ret = mxStreamManager.CreateMultipleStreams(pipelineConfig);
    if (ret != APP_ERR_OK) {
        LogError << GetError(ret) << "Failed to create Stream.";
        return ret;
    }
    // 读取测试图片
    MxStream::MxstDataInput dataBuffer;
    ret = ReadFile("data/test.jpg", dataBuffer);
    if (ret != APP_ERR_OK) {
        LogError << GetError(ret) << "Failed to read image file.";
        return ret;
    }
    std::string streamName = "classification";
    int inPluginId = 0;
    // 发送测试图片到Stream进行推理
    ret = mxStreamManager.SendData(streamName, inPluginId, dataBuffer);
    if (ret != APP_ERR_OK) {
        LogError << GetError(ret) << "Failed to send data to stream.";
        delete dataBuffer.dataPtr;
        dataBuffer.dataPtr = nullptr;
        return ret;
    }
    // 获取推理结果
    MxStream::MxstDataOutput* output = mxStreamManager.GetResult(streamName, inPluginId);
    if (output == nullptr) {
        LogError << "Failed to get pipeline output.";
        delete dataBuffer.dataPtr;
        dataBuffer.dataPtr = nullptr;
        return ret;
    }
    // 打印推理结果
    std::string result = std::string((char *)output->dataPtr, output->dataSize);
    LogInfo << "Results:" << result;

    // 销毁Stream
    mxStreamManager.DestroyAllStreams();
    delete dataBuffer.dataPtr;
    dataBuffer.dataPtr = nullptr;

    delete output;
    return 0;
}

4、Python源码详解

if __name__ == '__main__':
    # 初始化 Stream manager 资源
    streamManagerApi = StreamManagerApi()
    ret = streamManagerApi.InitManager()
    if ret != 0:
        print("Failed to init Stream manager, ret=%s" % str(ret))
        exit()

    # 根据指定的pipeline配置创建Stream
    with open("data/pipeline/Sample.pipeline", 'rb') as f:
        pipelineStr = f.read()
    ret = streamManagerApi.CreateMultipleStreams(pipelineStr)
    if ret != 0:
        print("Failed to create Stream, ret=%s" % str(ret))
        exit()

    # 读取测试图片
    dataInput = MxDataInput()
    with open("data/test.jpg", 'rb') as f:
        dataInput.data = f.read()

    # 发送测试图片到Stream进行推理
    streamName = b'classification'
    inPluginId = 0
    uniqueId = streamManagerApi.SendDataWithUniqueId(streamName, inPluginId, dataInput)
    if uniqueId < 0:
        print("Failed to send data to stream.")
        exit()

    # 获取推理结果
    inferResult = streamManagerApi.GetResultWithUniqueId(streamName, uniqueId, 3000)
    if inferResult.errorCode != 0:
        print("GetResultWithUniqueId error. errorCode=%d, errorMsg=%s" % (
            inferResult.errorCode, inferResult.data.decode()))
        exit()

    # 打印推理结果
    print(inferResult.data.decode())

    # 销毁Stream
    streamManagerApi.DestroyAllStreams()

标签:MindX,mobilenet,05,--,mxpi,sh,root,SDK
From: https://www.cnblogs.com/hiascend/p/17031331.html

相关文章