基于Paddle Serving&百度智能边缘BIE的边缘AI解决方案
Posted 百度大脑
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了基于Paddle Serving&百度智能边缘BIE的边缘AI解决方案相关的知识，希望对你有一定的参考价值。
Paddle Serving 作为飞桨（PaddlePaddle）开源的服务化部署框架，提供了 C++ Serving 和 Python Pipeline 两套框架，旨在帮助深度学习开发者和企业提供高性能、灵活易用的工业级在线推理服务，助力人工智能落地应用。
在最新的 Paddle Serving v0.7.0 中，提供了丰富的模型示例，总计有42个，具体模型信息可查看 Model_Zoo：
https://github.com/PaddlePaddle/Serving/blob/v0.7.0/doc/Model_Zoo_CN.md
百度智能云天工智能边缘（Baidu Intelligent Edge，BIE）由云端管理平台和BAETYL 开源边缘计算框架两部分组成，实现将云计算能力拓展至用户现场，可以提供临时离线、低延时的计算服务，包括消息规则、函数计算、AI 推断。智能边缘配合百度智能云，形成“云管理，端计算”的端云一体解决方案。
通过 Paddle Serving 赋能 BIE，可以实现产业级的边缘 AI 服务发布解决方案，达到如下的云边端能力：
管理边缘节点：纳管多种类型的边缘节点，包括服务器、边缘计算盒子。如果边缘侧是一个多机集群，也支持通过 BIE 统一管理。
状态检查：支持监控边缘节点运行状态、资源使用（CPU、内存、GPU、磁盘、网络流量等）。
下发 Serving：支持云端将 Paddle Serving 下发至边缘侧，作为边缘侧服务化推理+Serving 版本升级。
下发模型：支持云端动态下发 PaddlePaddle 模型至边缘侧，模型版本升级。
以下教程详细描述使用 Paddle Serving 和 BIE 实现云边端服务发布的能力。主要包括实验准备、模型准备、Paddle Serving 镜像准备、模型应用创建、模型应用部署、测试验证、测试效果展示。
1、试验设备：
一台 x86 架构的 ubuntu 18.04 虚拟机，不依赖 GPU
2、模型文件准备：
2.1在宿主机上下载 Paddle Serving 代码
git clone https://github.com/PaddlePaddle/Serving.git>>>向左滑动查看全部代码
2.2下载模型，参考文档详见如下链接：
https://github.com/PaddlePaddle/Serving/tree/v0.7.0/examples/Pipeline/PaddleDetection/yolov3
# 进入到yolov3实例模型目录
cd Serving/examples/Pipeline/PaddleDetection/yolov3/
# 下载模型
wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/yolov3_darknet53_270e_coco.tar
# 解压模型
tar xf yolov3_darknet53_270e_coco.tar
# 解压以后删除模型压缩包
rm -r yolov3_darknet53_270e_coco.tar>>>向左滑动查看全部代码
2.3制作模型压缩包
cd Serving/examples/Pipeline/PaddleDetection/yolov3/
压缩当前目录下的文件
zip -r paddle_serving_yolov3_darknet53_270e_coco.zip ./*
# 查看md5
md5sum paddle_serving_yolov3_darknet53_270e_coco.zip
7a2ca27f2f444c6ac169d19922ff89ab paddle_serving_yolov3_darknet53_270e_coco.zip>>>向左滑动查看全部代码
2.4将模型上传到 bos
3、Paddle Serving 镜像准备
3.1下载 Paddle Serving 开发镜像
docker pull registry.baidubce.com/paddlepaddle/serving:0.7.0-devel>>>向左滑动查看全部代码
3.2运行 Paddle Serving 开发镜像
docker run --rm -dit --name pipeline_serving_demo registry.baidubce.com/paddlepaddle/serving:0.7.0-devel bash>>>向右滑动查看全部代码
3.3Paddle Serving 开发镜像当中安装依赖程序
# 进入容器
docker exec -it pipeline_serving_demo bash
# 下载代码
git clone https://github.com/PaddlePaddle/Serving.git
# 进入Paddle Serving代码目录
cd Serving
# 安装依赖
pip3 install -r python/requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
# CPU环境安装内容如下
# 安装Paddle Serving
pip3 install paddle-serving-client==0.7.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install paddle-serving-server==0.7.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install paddle-serving-app==0.7.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
# 安装Paddle相关Python库
pip3 install paddlepaddle==2.2.0>>>向左滑动查看全部代码
加上-i https://pypi.tuna.tsinghua.edu.cn/simple表示使用国内源，提升下载速度，非必须，可以不加。
3.4提交镜像，固化上面的安装内容
docker commit pipeline_serving_demo paddle_serving:0.7.0-cpu-py36>>>向左滑动查看全部代码
这里将制作的镜像推送到了百度公有云 CCR，可以直接下载使用
docker pull registry.baidubce.com/pp/paddle-serving:0.7.0-cpu-py36>>>向左滑动查看全部代码
4、模型应用创建
4.1创建模型文件配置项
①创建配置项 paddle-yolov3-model
②点击引入文件
类型：HTTP
URL：
https://bie-document.gz.bcebos.com/paddlepaddle/paddle_serving_yolov3_darknet53_270e_coco.zip
文件名称：
paddle_serving_yolov3_darknet53_270e_coco.zip
是否解压：是
4.2创建启动脚本配置项
①创建配置项 paddle-yolov3-run-script
②添加配置数据如下
变量名：run.sh
变量值：如下述代码
#! /usr/bin/env bash
cd /home/work/yolov3
python3 web_service.py
4.3创建 paddle-serving 应用并挂载
①创建应用 paddle-serving
②配置服务
基础信息：
名称：paddle-serving
镜像：paddle-serving:0.7.0-cpu-py36
卷配置：
/home/work/script：运行脚本位置，与启动参数一致
/home/work/yolov3：模型位置，与运行脚本一致
启动参数
/bin/bash
/home/work/script/run.sh，与前面的卷配置一致
5、模型应用部署
5.1进入到 paddle-serving
5.2定位到目标节点，点击单节点匹配，选择目标节点 paddle-serving-test。等待几分钟，部署状态将变为已部署。
5.3进入边缘节点，可以查看服务在边缘测的运行状态，如下图所示：
6、测试验证
6.1使用 paddle-serving-client 验证
①ssh 登录边缘节点
②查看边缘节点 BIE 应用状态
kubectl get pod -n baetyl-edge
NAME READY STATUS RESTARTS AGE
paddle-serving-dd6d8986c-d89k7 1/1 Running 0 3m7s>>>向左滑动查看全部代码
③进入边缘容器
kubectl exec -it paddle-serving-dd6d8986c-d89k7 -n baetyl-edge /bin/bash
# 进去以后，工作目录为/home
λ paddle-serving-dd6d8986c-d89k7 /home
# 查看/home/work目录，检查云端模型是否下发成功
λ paddle-serving-dd6d8986c-d89k7 /home/work cd /home/work/
λ paddle-serving-dd6d8986c-d89k7 /home/work ls
script/ yolov3/>>>向左滑动查看全部代码
④执行测试命令
# 进入yolov3目录
λ paddle-serving-dd6d8986c-d89k7 /home/work/yolov3 cd /home/work/yolov3/
# 查看内容
λ paddle-serving-dd6d8986c-d89k7 /home/work/yolov3 ls -l
total 221M
--rw-r-- 1 root root 136K Dec 17 09:21 000000570688.jpg
-rw-rw-r-- 1 root root 509 Dec 17 09:21 benchmark_config.yaml
-rw-rw-r-- 1 root root 4.2K Dec 17 09:21 benchmark.py
-rw-rw-r-- 1 root root 2.1K Dec 17 09:21 benchmark.sh
-rw-rw-r-- 1 root root 1.5K Dec 17 09:21 config.yml
-rw-rw-r-- 1 root root 621 Dec 17 09:21 label_list.txt
-rwxr-xr-x 1 root root 220M Dec 17 09:21 paddle_serving_yolov3_darknet53_270e_coco.zip
-rw-rw-r-- 1 root root 1.2K Dec 17 09:21 pipeline_http_client.py
drwxr-xr-x 2 root root 4.0K Dec 17 09:26 PipelineServingLogs/
-rw-r--r-- 1 root root 89 Dec 17 09:26 ProcessInfo.json
-rw-rw-r-- 1 root root 368 Dec 17 09:21 README_CN.md
-rw-rw-r-- 1 root root 374 Dec 17 09:21 README.md
drwxr-xr-x 2 root root 4.0K Dec 17 09:21 serving_client/
drwxr-xr-x 2 root root 4.0K Dec 17 09:21 serving_server/
-rw-rw-r-- 1 root root 2.8K Dec 17 09:21 web_service.py
λ paddle-serving-dd6d8986c-d89k7 /home/work/yolov3 python3
# 执行客户端测试脚本
pipeline_http_client.py>>>向左滑动查看全部代码
返回结果如下：
'err_no': 0,
'err_msg': '',
'key': ['bbox_result'],
'value': ["['category_id': 0, 'bbox': [215.16099548339844, 438.1199951171875, 43.29920959472656, 186.94189453125], 'score': 0.9860591292381287, 'category_id': 0, 'bbox': [404.882568359375, 463.1432800292969, 50.00750732421875, 174.96109008789062], 'score': 0.972165584564209, 'category_id': 0, 'bbox': [259.8436279296875, 458.67169189453125, 47.04876708984375, 154.5758056640625], 'score': 0.9670743346214294, 'category_id': 0, 'bbox': [438.247314453125, 491.875, 68.9227294921875, 145.5482177734375], 'score': 0.9092186689376831, 'category_id': 0, 'bbox': [156.2906951904297, 505.449951171875, 57.74359130859375, 55.9661865234375], 'score': 0.7775811553001404, 'category_id': 0, 'bbox': [28.40601921081543, 451.0614318847656, 27.93486213684082, 113.30917358398438], 'score': 0.768792986869812, 'category_id': 0, 'bbox': [297.4198303222656, 511.6090087890625, 59.18255615234375, 76.463134765625], 'score': 0.7284609079360962, 'category_id': 0, 'bbox': [498.0811767578125, 504.2102966308594, 35.239501953125, 134.76394653320312], 'score': 0.6112859845161438, 'category_id': 0, 'bbox': [522.001708984375, 479.5540466308594, 63.42236328125, 156.11416625976562], 'score': 0.5191890001296997, 'category_id': 0, 'bbox': [139.90167236328125, 483.0037841796875, 21.444671630859375, 69.7462158203125], 'score': 0.43779468536376953, 'category_id': 0, 'bbox': [91.08878326416016, 494.5179748535156, 27.569290161132812, 55.932159423828125], 'score': 0.4112253189086914, 'category_id': 0, 'bbox': [9.615033149719238, 462.5943908691406, 21.810187339782715, 82.98226928710938], 'score': 0.3453913629055023, 'category_id': 0, 'bbox': [395.7669372558594, 460.096923828125, 13.82818603515625, 51.9017333984375], 'score': 0.30560365319252014, 'category_id': 0, 'bbox': [120.70891571044922, 496.8610534667969, 25.293846130371094, 54.288909912109375], 'score': 0.21395830810070038, 'category_id': 0, 'bbox': [595.8244018554688, 466.6758117675781, 6.93212890625, 22.802978515625], 'score': 0.212965726852417, 'category_id': 0, 'bbox': [624.6640625, 466.89288330078125, 6.6031494140625, 23.390869140625], 'score': 0.1309354156255722, 'category_id': 0, 'bbox': [71.72364807128906, 493.44171142578125, 23.06365966796875, 58.178955078125], 'score': 0.11486723273992538, 'category_id': 0, 'bbox': [93.5279769897461, 494.7836608886719, 18.048110961914062, 29.617156982421875], 'score': 0.0973864197731018, 'category_id': 0, 'bbox': [633.90625, 466.93377685546875, 5.08349609375, 22.541259765625], 'score': 0.08928193151950836, 'category_id': 0, 'bbox': [616.2327880859375, 467.5227966308594, 6.6636962890625, 22.73602294921875], 'score': 0.07480660825967789, 'category_id': 0, 'bbox': [330.21514892578125, 460.61785888671875, 14.3568115234375, 50.36322021484375], 'score': 0.05391114205121994, 'category_id': 0, 'bbox': [623.5628662109375, 521.3399047851562, 15.6580810546875, 118.66009521484375], 'score': 0.05177609249949455, 'category_id': 0, 'bbox': [118.22535705566406, 493.11846923828125, 15.311538696289062, 46.67529296875], 'score': 0.05106724426150322, 'category_id': 0, 'bbox': [76.89163970947266, 489.4934997558594, 14.865859985351562, 36.153900146484375], 'score': 0.0509687103331089, 'category_id': 0, 'bbox': [612.2092895507812, 466.2706604003906, 6.8411865234375, 24.82183837890625], 'score': 0.04965047165751457, 'category_id': 0, 'bbox': [459.98687744140625, 466.3093566894531, 11.68914794921875, 34.41339111328125], 'score': 0.04907878115773201, 'category_id': 0, 'bbox': [0.4039268493652344, 462.4938049316406, 10.412893295288086, 61.628326416015625], 'score': 0.048166826367378235, 'category_id': 0, 'bbox': [163.0106201171875, 501.29864501953125, 14.077667236328125, 28.6602783203125], 'score': 0.043710850179195404, 'category_id': 0, 'bbox': [42.41417694091797, 456.0679626464844, 17.12506103515625, 96.23989868164062], 'score': 0.043581727892160416, 'category_id': 0, 'bbox': [124.59736633300781, 495.2655029296875, 14.957061767578125, 29.24896240234375], 'score': 0.032280560582876205, 'category_id': 0, 'bbox': [322.8830261230469, 510.5441589355469, 35.19915771484375, 58.528839111328125], 'score': 0.032096412032842636, 'category_id': 0, 'bbox': [499.7272644042969, 472.0701599121094, 6.73431396484375, 23.52752685546875], 'score': 0.03191200643777847, 'category_id': 0, 'bbox': [635.601318359375, 472.9556579589844, 4.2603759765625, 17.8453369140625], 'score': 0.03138304129242897, 'category_id': 0, 'bbox': [13.47295093536377, 509.2365417480469, 17.922499656677246, 59.210113525390625], 'score': 0.024998517706990242, 'category_id': 0, 'bbox': [492.8521728515625, 474.7392883300781, 5.19732666015625, 15.8018798828125], 'score': 0.02452804334461689, 'category_id': 0, 'bbox': [141.70277404785156, 491.10888671875, 16.059814453125, 34.2940673828125], 'score': 0.01741969771683216, 'category_id': 0, 'bbox': [111.90968322753906, 493.1148986816406, 13.242355346679688, 30.584503173828125], 'score': 0.016763748601078987, 'category_id': 0, 'bbox': [70.63130950927734, 495.74530029296875, 15.302810668945312, 42.497802734375], 'score': 0.016103360801935196, 'category_id': 0, 'bbox': [499.5566711425781, 506.34857177734375, 30.214935302734375, 69.9669189453125], 'score': 0.014152972027659416, 'category_id': 2, 'bbox': [500.8828125, 460.91827392578125, 13.79754638671875, 11.3291015625], 'score': 0.05771809071302414, 'category_id': 2, 'bbox': [492.967529296875, 461.03411865234375, 16.8121337890625, 11.01202392578125], 'score': 0.050255682319402695, 'category_id': 2, 'bbox': [566.1650390625, 461.9089050292969, 14.287353515625, 11.1707763671875], 'score': 0.04679763689637184, 'category_id': 2, 'bbox': [582.1019287109375, 463.1806335449219, 11.535888671875, 9.76470947265625], 'score': 0.03930026665329933, 'category_id': 2, 'bbox': [573.3811645507812, 463.0304260253906, 15.5157470703125, 9.6693115234375], 'score': 0.03414313867688179, 'category_id': 2, 'bbox': [600.5574951171875, 462.50701904296875, 7.7860107421875, 8.21221923828125], 'score': 0.025939688086509705, 'category_id': 2, 'bbox': [486.56951904296875, 463.8977966308594, 12.2598876953125, 7.6630859375], 'score': 0.022135090082883835, 'category_id': 25, 'bbox': [437.3040466308594, 545.1283569335938, 38.20965576171875, 87.29931640625], 'score': 0.018933355808258057, 'category_id': 26, 'bbox': [29.908803939819336, 486.8944396972656, 16.05537223815918, 22.83355712890625], 'score': 0.04068344458937645, 'category_id': 26, 'bbox': [581.0633544921875, 620.1477661132812, 32.0316162109375, 18.63525390625], 'score': 0.039497870951890945, 'category_id': 26, 'bbox': [385.1318359375, 517.0343017578125, 18.244873046875, 13.5072021484375], 'score': 0.02217845804989338, 'category_id': 26, 'bbox': [590.1017456054688, 559.3590698242188, 13.1651611328125, 43.9588623046875], 'score': 0.015419745817780495, 'category_id': 26, 'bbox': [582.7347412109375, 560.3289184570312, 26.631103515625, 76.6273193359375], 'score': 0.014936945401132107, 'category_id': 33, 'bbox': [460.7890930175781, 336.1373291015625, 17.67572021484375, 23.1480712890625], 'score': 0.8834899663925171, 'category_id': 33, 'bbox': [319.202880859375, 214.55738830566406, 142.63299560546875, 70.57722473144531], 'score': 0.8617939949035645, 'category_id': 33, 'bbox': [233.26974487304688, 29.542848587036133, 9.237213134765625, 9.067476272583008], 'score': 0.8452507257461548, 'category_id': 33, 'bbox': [175.90914916992188, 314.95672607421875, 79.74258422851562, 29.947021484375], 'score': 0.820819079875946, 'category_id': 33, 'bbox': [504.2533874511719, 261.376708984375, 18.829742431640625, 24.36407470703125], 'score': 0.8137103915214539, 'category_id': 33, 'bbox': [328.5792236328125, 86.0416030883789, 61.03375244140625, 27.46881103515625], 'score': 0.8071057796478271, 'category_id': 33, 'bbox': [363.2680358886719, 161.7618865966797, 12.36090087890625, 10.89990234375], 'score': 0.8044251203536987, 'category_id': 33, 'bbox': [222.79953002929688, 350.03302001953125, 162.13482666015625, 79.5477294921875], 'score': 0.7996627688407898, 'category_id': 33, 'bbox': [279.99066162109375, 124.66069030761719, 45.8681640625, 16.145660400390625], 'score': 0.7842240333557129, 'category_id': 33, 'bbox': [98.05622100830078, 419.7298889160156, 65.67034149169922, 62.50732421875], 'score': 0.7424381971359253, 'category_id': 33, 'bbox': [242.89645385742188, 166.64027404785156, 20.291900634765625, 14.35076904296875], 'score': 0.6263655424118042, 'category_id': 33, 'bbox': [430.3121643066406, 40.18694305419922, 18.87353515625, 19.074172973632812], 'score': 0.5938690304756165, 'category_id': 33, 'bbox': [86.46560668945312, 137.0863800048828, 48.230865478515625, 19.82879638671875], 'score': 0.5937690734863281, 'category_id': 33, 'bbox': [392.02850341796875, 394.45611572265625, 26.37896728515625, 23.63372802734375], 'score': 0.5023226141929626, 'category_id': 33, 'bbox': [271.4128112792969, 299.25018310546875, 149.4326171875, 59.794921875], 'score': 0.422481894493103, 'category_id': 33, 'bbox': [282.4754638671875, 281.77496337890625, 164.82354736328125, 56.41583251953125], 'score': 0.4141545295715332, 'category_id': 33, 'bbox': [114.94490051269531, 237.0370330810547, 22.510589599609375, 17.687591552734375], 'score': 0.40582510828971863, 'category_id': 33, 'bbox': [160.378173828125, 257.062255859375, 10.08685302734375, 8.29095458984375], 'score': 0.3285631537437439, 'category_id': 33, 'bbox': [260.0093994140625, 44.60060501098633, 4.9671630859375, 5.313697814941406], 'score': 0.28955695033073425, 'category_id': 33, 'bbox': [216.726318359375, 238.36724853515625, 180.0245361328125, 60.68719482421875], 'score': 0.25094327330589294, 'category_id': 33, 'bbox': [58.31337356567383, 340.7672424316406, 7.575717926025391, 5.21954345703125], 'score': 0.2317829728126526, 'category_id': 33, 'bbox': [2.293954849243164, 424.1985778808594, 17.95143699645996, 10.4171142578125], 'score': 0.21052710711956024, 'category_id': 33, 'bbox': [281.1366271972656, 130.51866149902344, 8.10662841796875, 9.679290771484375], 'score': 0.13495559990406036, 'category_id': 33, 'bbox': [170.76100158691406, 425.669677734375, 60.928955078125, 52.55987548828125], 'score': 0.11672469973564148, 'category_id': 33, 'bbox': [218.16445922851562, 236.66871643066406, 86.7357177734375, 36.82264709472656], 'score': 0.09928663074970245, 'category_id': 33, 'bbox': [57.59531021118164, 340.63653564453125, 11.535961151123047, 10.2398681640625], 'score': 0.09524064511060715, 'category_id': 33, 'bbox': [83.4229736328125, 300.5054626464844, 4.1660614013671875, 3.51611328125], 'score': 0.05346690118312836, 'category_id': 33, 'bbox': [85.83900451660156, 137.0255584716797, 7.1644134521484375, 8.851104736328125], 'score': 0.044692330062389374, 'category_id': 33, 'bbox': [412.9825744628906, 38.167327880859375, 32.94921875, 45.059669494628906], 'score': 0.04101773351430893, 'category_id': 33, 'bbox': [596.8782958984375, 1.0692591667175293, 35.0404052734375, 10.813299655914307], 'score': 0.03720707818865776, 'category_id': 33, 'bbox': [218.40847778320312, 239.14697265625, 37.585540771484375, 23.478668212890625], 'score': 0.03472490981221199, 'category_id': 33, 'bbox': [22.163543701171875, 430.1997985839844, 15.829334259033203, 46.72674560546875], 'score': 0.03383627161383629, 'category_id': 33, 'bbox': [51.58473205566406, 443.5025939941406, 30.812210083007812, 35.05010986328125], 'score': 0.028524775058031082, 'category_id': 33, 'bbox': [436.84979248046875, 541.2200927734375, 41.42523193359375, 93.6231689453125], 'score': 0.01658524200320244, 'category_id': 33, 'bbox': [577.9300537109375, 0.0, 54.505859375, 48.904815673828125], 'score': 0.016126543283462524, 'category_id': 33, 'bbox': [3.094654083251953, 438.25445556640625, 20.415660858154297, 28.048095703125], 'score': 0.014082299545407295, 'category_id': 56, 'bbox': [567.2755126953125, 559.4602661132812, 37.1573486328125, 77.50048828125], 'score': 0.3802623450756073, 'category_id': 56, 'bbox': [72.8006820678711, 514.73583984375, 21.915634155273438, 37.716796875], 'score': 0.08133123815059662, 'category_id': 56, 'bbox': [508.6803283691406, 559.0682373046875, 93.95669555664062, 78.7860107421875], 'score': 0.06216099485754967, 'category_id': 56, 'bbox': [174.71974182128906, 497.610595703125, 17.5482177734375, 22.37078857421875], 'score': 0.04738868027925491, 'category_id': 56, 'bbox': [90.97509002685547, 507.92376708984375, 28.04888916015625, 45.3680419921875], 'score': 0.03899860754609108, 'category_id': 56, 'bbox': [377.0034484863281, 491.5137023925781, 20.13714599609375, 34.996185302734375], 'score': 0.0388840027153492, 'category_id': 56, 'bbox': [503.78839111328125, 566.7881469726562, 28.494873046875, 72.017822265625], 'score': 0.036751069128513336, 'category_id': 56, 'bbox': [119.07683563232422, 507.221923828125, 28.098655700683594, 46.0355224609375], 'score': 0.029802320525050163, 'category_id': 56, 'bbox': [70.57160186767578, 499.4393310546875, 15.87109375, 51.1988525390625], 'score': 0.024599188938736916, 'category_id': 56, 'bbox': [389.9160461425781, 493.0232849121094, 14.80902099609375, 33.048980712890625], 'score': 0.019945451989769936, 'category_id': 56, 'bbox': [60.86790466308594, 502.6175537109375, 12.643905639648438, 27.7879638671875], 'score': 0.018364958465099335, 'category_id': 56, 'bbox': [529.2908935546875, 566.8236694335938, 40.3153076171875, 71.20458984375], 'score': 0.01757989637553692]"],
'tensors': []
>>>向左滑动查看全部代码
6.2使用 postman 验证
①我们知道上述 yolov3 模型服务的容器内端口是18082，当前我们需要在单独的一台测试机器上使用 postman 去调用 yolov3 服务接口，那么就需要将容器内的18082端口映射到宿主机上，我们在云端 BIE 控制台配置 paddle-serving 这个服务，添加端口映射，如下图所示：
②下载测试图片 dog.jpeg
下载地址：
https://bce.bdstatic.com/doc/bce-doc/BIE/dog_831f56a.jpeg
③执行一下命令，将这张图片的 base64 编码输出到 dog.base64 文件当中
base64 -i dog.jpeg -o dog.base64④组装 postman 输出参数，如下所示：
"key":[
"image"
],
"value":[
"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以上是关于基于Paddle Serving&百度智能边缘BIE的边缘AI解决方案的主要内容，如果未能解决你的问题，请参考以下文章
基于百度Paddle和NI Rio的人工智能自动化数据集训练
一行命令启动，十分钟内完成部署，Paddle Serving开放模型即服务功能
寒武纪与百度飞桨Paddle Lite完成适配 加速AI多场景落地