tensorflow安装教程_详解tensorflow基础知识

tensorflow安装教程_详解tensorflow基础知识 一、基于docker安装TF-Serving参考文档：https://tensorflow.google.cn/tfx/serving/dockerhttps://zhuanlan.zhihu.com/p/45109194基于docker的安装首先需要安装docker在docker的下载地址https://download.docker.com/linux/ubuntu/dists/中查找ubuntu对应的版本查看ubuntu版本：cat /proc/version查看详细信息：lsb_release -a可以看到ubuntu的代号名称为：xenial，cput为AMD64 因此到文件夹中去选取对应版本的文件：获取.deb安装文件：wget https://download.docker.com/linux/ubuntu/dists/xenial/pool/stable/amd64/docker-ce_18.03.0~ce-0~ubuntu_amd64.deb使用dpkg命令进行安装：dpkg -I docker-ce_18.03.0~ce-0~ubuntu_amd64.deb执行hello-world测试是否安装成功：用dpkg命令安装后有遇到过docker没有正常启动的问题，好像是缺失mkl还是systemstl 没有启动docker，忘了记录，后续有同学遇到再补充。

在docker中启动服务准备docker环境docker pull tensorflow/serving这个命令会获取一个预先安装好的虚拟环境，可以在docker中 *** 作虚拟环境，TensorflowServing提供两种形式的调用：RestFull和GRPC一、RestFull API调用下载tfserving的示例代码mkdir tfservingcd tfservinggit clone https://github.com/tensorflow/serving运行TF Servingdocker run -p 8501:8501 --mount type=bind,source=/root/maoyaozong/tfserving/serving/tensorflow_serving/servables/tensorflow/testdata/saved_model_half_plus_two_cpu,target=/models/half_plus_two -eMODEL_NAME=half_plus_two-ttensorflow/serving这里提供8501端口作为REST API的端口号，绑定了模型的原始地址，并且命名模型的名称model_name=half_plus_two客户端验证curl -d'{"instances": [1.0, 2.0, 5.0]}' -X POST http://localhost:8501/v1/models/half_plus_two:predict获取返回结果{ "predictions": [2.5, 3.0, 4.5] }二、GRPC API调用下载tfserving的示例代码mkdir tfservingcd tfservinggit clone https://github.com/tensorflow/serving模型编译/root/anaconda3/bin/pythontensorflow_serving/example/mnist_saved_model.py models/mnist在目录下会多出一个models的文件夹，用来存储模型运行TF Servingdockerrun -p 8500:8500 --mounttype=bind,source=$(pwd)/models/mnist,target=/models/mnist -e MODEL_NAME=mnist -t tensorflow/serving安装tensorflow-serving-apipip install tensorflow-serving-api客户端验证/root/anaconda3/bin/pythontensorflow_serving/example/mnist_client.py --num_tests=1000--server=127.0.0.1:8500Inference error rate: 10.4%二、直接安装tensorflow_model_server移除已经安装的tensorflow_model_serverapt-getremove tensorflow-model-server把Serving的发型URI添加为package源echo "deb[arch=amd64] http://storage.googleapis.com/tensorflow-serving-apt stabletensorflow-model-server tensorflow-model-server-universal" | sudo tee/etc/apt/sources.list.d/tensorflow-serving.list && curlhttps://storage.googleapis.com/tensorflow-serving-apt/tensorflow-serving.release.pub.gpg| sudo apt-key add –安装tensorflow modelServerapt-getupdate && apt-get install tensorflow-model-server通过tensorflow_model_server启动服务tensorflow_model_server--port=8502 --rest_api_port=8503 --model_name=half_plus_two--model_base_path=/root/maoyaozong/tfserving/serving/tensorflow_serving/servables/tensorflow/testdata/saved_model_half_plus_two_cpu这里我们启动了8502作为gRPC端口，8503作为restFull端口验证服务curl-d '{"instances": [1.0, 2.0, 5.0]}' -X POST http://localhost:8503/v1/models/half_plus_two:predict