1.github
https://github.com/FederatedAI/FATE
2.下载源码
git clone https://github.com/FederatedAI/FATE.git
3.单机版--docerk部署
3.1 安装docker
3.2 安装dockercompose
curl -L https://github.com/docker/compose/releases/download/1.23.0-rc3/docker-compose-`uname -s`-`uname -m` -o /usr/local/bin/docker-compose
sudo chmod +x /usr/local/bin/docker-compose
3.3 docker构建和运行
cd FATE/standalone-deploy
sudo sh build_standalone_docker.sh
此时能看到docker打包的过程,运行完成之后,docker ps能看到fate_fateboard和fate_python连个容器。
3.4 测试fate
CONTAINER_ID=`docker ps -aqf "name=fate_python"`
docker exec -t -i ${CONTAINER_ID} bash
sh ./federatedml/test/run_test.sh
3.5 在容器运行example
3.5.1 训练
/fate/examples/federatedml-1.0-examples# python quick_run.py
3.5.2 预测
把quick_run.py的TASK='train'注释掉,取消TASK='predict'注释,然后运行python quick_run.py
3.6 在http://localhost:8080能看到fate的dashboard。