tensorflow的模型使用flask制作windows系统服务

搜罗到两种方案，经测试都可正常运行。这两种方案各有利弊，可根据实际需求选择。

1. nssm的方案

   将tensorflow模型的推理逻辑制作成flask服务，假设文件为app.py。其中的model_predict需要换成用户自己的推理模块。

   # app.py文件
   from flask import Flask, request
   import numpy as np
   from tensorflow.python.saved_model import tag_constants
   from tensorflow.contrib.tensor_forest.python import tensor_forest
   from tensorflow.python.ops import resources
   import tensorflow.compat.v1 as tf
   import json
   from gevent import pywsgi
   import multiprocessing
   from multiprocessing import freeze_support
   from datetime import datetime
   import platform
   
   app = Flask(__name__)
   
   class predict():
       def __init__(self, model_path):
           # with tf.Session() as self.sess:
           self.sess = tf.Session()
           meta_graph_def = tf.saved_model.loader.load(self.sess, [tag_constants.SERVING], model_path + '/001/')
           signature = meta_graph_def.signature_def
           self.x = signature['prediction'].inputs['input'].name
           self.result = signature['prediction'].outputs['output'].name
   
       def run(self, input_data):
           _input_data = []
           _input_data.append(input_data)
           y = self.sess.run(self.result, feed_dict={self.x: _input_data})
           return y
   
   @app.route('/')
   def hello():
       return 'hello world'
   
   @app.route('/predict', methods=['POST'])
   def model_predict():
       input_json = request.get_json()
       method = input_json['method']
       input_data = input_json['data']
       if method != "inference":
           results = {'ret_code':101,'ret_message':'字段错误'}
           return json.dumps(results,ensure_ascii=False)
       input_arr = np.array(input_data)
       try:
           result = pred_infer.run(input_arr)[0]
           if (result[1] > 0.5):
               ret_status = 'good'
           else:
               ret_status = 'bad'
           ret_code = 100
           results = {'ret_code':ret_code,'ret_message':'处理成功','result':result.tolist(),'ret_status':ret_status}
       except:
           ret_code =  201
           results = {'ret_code':ret_code,'ret_message':'参数错误'}
               
       results_json = json.dumps(results,ensure_ascii=False)
       return results_json
   
   #model_path = '.\\models\\healthy\\model_state'
   model_path = 'D:\\YourModelPath\\models\\model_state'
   pred_infer = predict(model_path)
   
   def MyServer(host, port):
       server = pywsgi.WSGIServer((host, port), app)
       server.serve_forever()
   
   if __name__ == '__main__':
       MyServer('0.0.0.0', 8088)
   

   将python文件打包成exe文件。

   D:\Python36\Scripts\pyinstaller.exe -F .\app.py #dist目录下生成app.exe
   

   命令行测试app.exe能否正常运行，提供推理服务。

   下载nssm，使用nssm实现注册/开启/关闭/更新/移除服务。

   nssm\win32\nssm.exe install  appServer  #注册服务，appServer是服务名
   
   nssm\win32\nssm.exe start  appServer    #开启服务，appServer是服务名
   

2. pywin32的方案

   将tensorflow模型的推理逻辑改写成flask服务，假设文件为app.py(推理模块)和server.py(服务模块)。

   # app.py文件
   from flask import Flask, request
   import numpy as np
   from tensorflow.python.saved_model import tag_constants
   from tensorflow.contrib.tensor_forest.python import tensor_forest
   from tensorflow.python.ops import resources
   import tensorflow.compat.v1 as tf
   import json
   from gevent import pywsgi
   import multiprocessing
   from multiprocessing import freeze_support
   from datetime import datetime
   import platform
   
   app = Flask(__name__)
   
   class predict():
       def __init__(self, model_path):
           # with tf.Session() as self.sess:
           self.sess = tf.Session()
           meta_graph_def = tf.saved_model.loader.load(self.sess, [tag_constants.SERVING], model_path + '/001/')
           signature = meta_graph_def.signature_def
           self.x = signature['prediction'].inputs['input'].name
           self.result = signature['prediction'].outputs['output'].name
   
       def run(self, input_data):
           _input_data = []
           _input_data.append(input_data)
           y = self.sess.run(self.result, feed_dict={self.x: _input_data})
           return y
   
   @app.route('/')
   def hello():
       return 'hello world'
   
   @app.route('/predict', methods=['POST'])
   def model_predict():
       input_json = request.get_json()
       method = input_json['method']
       input_data = input_json['data']
       if method != "inference":
           results = {'ret_code':101,'ret_message':'字段错误'}
           return json.dumps(results,ensure_ascii=False)
       input_arr = np.array(input_data)
       try:
           result = pred_infer.run(input_arr)[0]
           if (result[1] > 0.5):
               ret_status = 'good'
           else:
               ret_status = 'bad'
           ret_code = 100
           results = {'ret_code':ret_code,'ret_message':'处理成功','result':result.tolist(),'ret_status':ret_status}
       except:
           ret_code =  201
           results = {'ret_code':ret_code,'ret_message':'参数错误'}
               
       results_json = json.dumps(results,ensure_ascii=False)
       return results_json
   
   #model_path = '.\\models\\healthy\\model_state'
   model_path = 'D:\\YourModelPath\\models\\model_state'
   pred_infer = predict(model_path)
   

   就是把WSGIServer调用的部分放到server.py中。拆分的原因很明显，解耦合，方便其他模型做服务时，只在app.py内改动。特别注意， 模型的路径需要用绝对路径，相对路径可以注册服务，但无法正常启动服务(闪退)。

   # server.py文件
   import win32serviceutil
   from gevent.pywsgi import WSGIServer
   from app import app
   
   class Service(win32serviceutil.ServiceFramework):
       # 服务名
       _svc_name_ = "flask_gevent_service_test"
       # 显示服务名
       _svc_display_name_ = "flask gevent service test display name"
       # 描述
       _svc_description_ = "flask gevent service test description"
   
       def __init__(self, *args):
           super().__init__(*args)
           # host和ip绑定
           self.http_server = WSGIServer(('127.0.0.1', 8088), app)
           self.SvcStop = self.http_server.stop
           self.SvcDoRun = self.http_server.serve_forever
   
   
   if __name__ == '__main__':
       win32serviceutil.HandleCommandLine(Service)
   

   使用python自带的pythonServer实现注册/开启/关闭/更新/移除服务。

   python server.py install  #注册服务
   python server.py start    #开启服务
   

   总结：在某些情况下无法使用nssm的方案，比如防火墙拦截等，这时可选择第二种方案。当然第二种方案的执行命令仍然需要python环境包，可以在此基础上将app.py和server.py两个文件打包成一个exe，方便移植。这部分操作读者可以参考第一种方案中的打包方法自行验证。