将tensorflow训练好的模型部署成sercice服务,并做预测

web框架用的是tornado，模型加载在上一篇博客已经提到，下面写了一个service.py文件:



    

  1. import tornado.web
    2. 

  2. import logging
    3. 

  3. import string
    4. 

  4. import os
    5. 

  5. import sys
    6. 

  6. from predict import predict
    7. 

    8. 

  8. logger = logging.getLogger('mylogger')
    9. 

  9. logger.setLevel(logging.DEBUG)
    10. 

  10. # 再创建一个handler，用于输出到控制台
    11. 

  11. ch = logging.StreamHandler()
    12. 

  12. ch.setLevel(logging.DEBUG)
    13. 

  13. # 定义handler的输出格式
    14. 

  14. formatter = logging.Formatter('%(asctime)s - %(message)s')
    15. 

  15. ch.setFormatter(formatter)
    16. 

  16. # 给logger添加handler
    17. 

  17. logger.addHandler(ch)
    18. 

  18. def work(text):
    19. 

  19.  if text is None:
    20. 

  20.  return 0.
    21. 

  21.  else:
    22. 

  22.  return predict(text)
    23. 

    24. 

  24. class MainHandler(tornado.web.RequestHandler):
    25. 

  25.  def post(self):
    26. 

  26.  text = self.get_argument('text')
    27. 

  27.  p = work(text)
    28. 

  28.  self.write(p)
    29. 

    30. 

  30. class IndexHandler(tornado.web.RequestHandler):
    31. 

  31.  def get(self):
    32. 

  32.  text = self.get_argument('text')
    33. 

  33.  p = work(text)
    34. 

  34.  self.render('index.html',text=text,result='{0}'.format(p))
    35. 

    36. 

    37. 

  37. application=tornado.web.Application(
    38. 

  38. handlers=[(r"/", MainHandler),
    39. 

  39.  (r'/demo', IndexHandler)],
    40. 

  40.  template_path=os.path.join(os.path.dirname(__file__), "templates")
    41. 

  41. )
    42. 

    43. 

  43. if __name__=='__main__':
    44. 

  44.  if len(sys.argv)<2:
    45. 

  45.  port=8410
    46. 

  46.  else:
    47. 

  47.  port=string.atoi(sys.argv[1])
    48. 

  48.  application.listen(port)
    49. 

  49.  logger.info('Starting server:port=%d, use <Ctrl-C> to stop' % port)
    50. 

  50.  tornado.ioloop.IOLoop.instance().start()
    51. 

    52. 





















templates/index.html问价内容：










    

  1. <!DOCTYPE html>
    2. 

  2. <html>
    3. 

  3.  <head><title>text abumse server</title></head>
    4. 

  4.  <body>
    5. 

  5.  <form method="get" action="/demo">
    6. 

  6.  <p>text content: <input type="text" name="text" value="{{text}}" style="width: 800px"><input type="submit"></p>
    7. 

  7.  </form>
    8. 

  8.  <p>{{result}}</p>
    9. 

  9.  <p><img src="{{text}}" width="600px"></p>
    10. 

  10.  </body>
    11. 

  11. </html>
    12. 











启动service.py文件:








    

  1. /anaconda/bin/python3 /Users/shuubiasahi/Documents/python/credit-tftextclassify-abuse/service.py
    2. 

  2. 2017-10-13 15:58:20.625704: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
    3. 

  3. 2017-10-13 15:58:20.625723: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
    4. 

  4. 2017-10-13 15:58:20.625728: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
    5. 

  5. 2017-10-13 15:58:20.625733: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
    6. 

  6. 2017-10-13 15:58:21,732 - Starting server:port=8410, use <Ctrl-C> to stop
    7. 













监控的是8410端口，可以启动在浏览器输入http://localhost:8410/demo?text=我操，日狗了，如下：



将tensorflow训练好的模型部署成sercice服务,并做预测








将tensorflow训练好的模型部署成sercice服务,并做预测











将tensorflow训练好的模型部署成sercice服务,并做预测







将tensorflow训练好的模型部署成sercice服务,并做预测本身我是用的cnn做的辱骂识别模型，预测的概率还挺高，看到最后别喷啊 ，哈哈哈哈。。。。。





 
                    
            
                

                  
 
        

	 
        

            

                                            

        

        
相关文章：

        

      
            
 
                    
    
                                            

               
   
         

    


  






 
          

    
猜你喜欢 

        
    
                        

   
 



    
相关资源 

        
    
              
                            

   

   
    

     
相似解决方案 

         
    
                          

    

  
   

    

 
   

    
热门标签  

    

                    Java
                        Python
                        linux
                        javascript
                        Mysql
                        C#
                        Docker
                        算法
                        前端
                        SpringBoot
                        Redis
                        Vue
                        spring
                        设计模式
                        .net core
                        .net
                        kubernetes
                        c++
                        数据库
                        数据结构
                        大数据
                        js
                        机器学习
                        微服务
                        Android
                        Go
                        程序员
                        面试
                        JVM
                        ASP.net core
                        云原生
                        人工智能
                        后端
                        PHP
                        git
                        CSS
                        golang
                        k8s
                        Nginx
                        Django
                        mybatis
                        深度学习
                        多线程
                        React
                        架构
                        devops
                        爬虫
                        云计算
                        Spring Boot
                        LeetCode