Created by: MRXLT

http预测时client端发送的请求格式改为{"feed":[sample1, sample2], "fetch":["fetch_name"]}，返回结果中每个fetch_name对应的数据为一个batch的预测结果， 以fit_a_line示例为例， client请求

curl -H "Content-Type:application/json" -X POST -d '{"feed":[{"x": [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]}, {"x": [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]}], "fetch":["price"]}' http://127.0.0.1:9393/uci/prediction

收到

{"result":{"price":[[18.901151657104492],[18.901151657104492]]}}