提交 78a7a868 编写于 作者: M MRXLT

fix conflict

上级 c2d6ee03
...@@ -228,14 +228,6 @@ curl -H "Content-Type:application/json" -X POST -d '{"url": "https://paddle-serv ...@@ -228,14 +228,6 @@ curl -H "Content-Type:application/json" -X POST -d '{"url": "https://paddle-serv
| Description | Get click probability from a feature vector of item | | Description | Get click probability from a feature vector of item |
| Key | Value |
| :----------------- | :----------------------------------------------------------- |
| Model Name | DNN-CTR(with cube) |
| URL | https://paddle-serving.bj.bcebos.com/unittest/ctr_cube_unittest.tar.gz |
| Client/Server Code | https://github.com/PaddlePaddle/Serving/tree/develop/python/examples/criteo_ctr_with_cube |
| Description | Get click probability from a feature vector of item |
<h2 align="center">Document</h2> <h2 align="center">Document</h2>
### New to Paddle Serving ### New to Paddle Serving
......
...@@ -220,14 +220,6 @@ curl -H "Content-Type:application/json" -X POST -d '{"url": "https://paddle-serv ...@@ -220,14 +220,6 @@ curl -H "Content-Type:application/json" -X POST -d '{"url": "https://paddle-serv
| Key | Value |
| :----------------- | :----------------------------------------------------------- |
| 模型名 | DNN-CTR(with cube) |
| 下载链接 | https://paddle-serving.bj.bcebos.com/unittest/ctr_cube_unittest.tar.gz |
| 客户端/服务端代码 | https://github.com/PaddlePaddle/Serving/tree/develop/python/examples/criteo_ctr_with_cube |
| 介绍 | 从项目的特征向量中获得点击概率 |
<h2 align="center">文档</h2> <h2 align="center">文档</h2>
### 新手教程 ### 新手教程
......
...@@ -61,4 +61,7 @@ def single_func(idx, resource): ...@@ -61,4 +61,7 @@ def single_func(idx, resource):
multi_thread_runner = MultiThreadRunner() multi_thread_runner = MultiThreadRunner()
result = multi_thread_runner.run(single_func, args.thread, {}) result = multi_thread_runner.run(single_func, args.thread, {})
print(result) avg_cost = 0
for cost in result[0]:
avg_cost += cost
print("total cost of each thread".format(avg_cost / args.thread))
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册