mirrors
/
Smart_container
mirror of https://github.com/ColugoMum/Smart_container.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update readme_industry.md

pull/1/head
thomas-yanxin 2021-12-20 00:34:47 +08:00 committed by GitHub
parent 2a6db34e8b
commit eb194fde4c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/readme_industry.md
View File

@ -209,7 +209,7 @@ python python/predict_rec.py -c configs/inference_rec.yaml -o Global.rec_infere
## 模型部署
### 1. 简介
<!-- ### 1. 简介
[Paddle Serving](https://github.com/PaddlePaddle/Serving) 旨在帮助深度学习开发者轻松部署在线预测服务，支持一键部署工业级的服务能力、客户端和服务端之间高并发和高效通信、并支持多种编程语言开发客户端。
该部分以 HTTP 预测服务部署为例，介绍怎样在 PaddleClas 中使用 PaddleServing 部署模型服务。
@ -331,7 +331,7 @@ python3 recognition_web_service.py &>log.txt &
python3 pipeline_http_client.py
```
成功运行后，模型预测的结果会打印在cmd窗口中，结果示例为：
![](https://github.com/PaddlePaddle/PaddleClas/raw/release/2.3/deploy/paddleserving/imgs/results_shitu.png)
![](https://github.com/PaddlePaddle/PaddleClas/raw/release/2.3/deploy/paddleserving/imgs/results_shitu.png) -->
在项目中为用户提供了基于服务器的部署Demo方案。用户可根据实际情况自行参考。