riyun1989

> 1.如果要使用[http://127.0.0.1:9292/uci/prediction这个url，请使用examples/C++/fit_a_line/test_server.py启动服务。](http://127.0.0.1:9292/uci/prediction%E8%BF%99%E4%B8%AAurl%EF%BC%8C%E8%AF%B7%E4%BD%BF%E7%94%A8examples/C++/fit_a_line/test_server.py%E5%90%AF%E5%8A%A8%E6%9C%8D%E5%8A%A1%E3%80%82) 2.如果使用python3 -m paddle_serving_server.serve --model uci_housing_model --thread 10 --port 9292启动服务，请使用 > > ``` > curl -XPOST http://127.0.0.1:9292/GeneralModelService/inference -d '{"tensor":[{"float_data":[0.0137,-0.1136,0.2553,-0.0692,0.0582,-0.0727,-0.1583,-0.0584,0.6283,0.4919,0.1856,0.0795,-0.0332],"elem_type":1,"name":"x","alias_name":"x","shape":[1,13]}],"fetch_var_names":["price"],"log_id":0}' > ``` > > 请求服务。具体的说明[https://github.com/PaddlePaddle/Serving/blob/v0.9.0/doc/C%2B%2B_Serving/Http_Service_CN.md。](https://github.com/PaddlePaddle/Serving/blob/v0.9.0/doc/C%2B%2B_Serving/Http_Service_CN.md%E3%80%82) 我也在这卡了好久。找了好久才找到。希望能帮到你。 被官方文档误导了