TensorFlow Serving：在运行时更新 model_config（添加其他模型）

Question

我正忙于配置 TensorFlow Serving 客户端，该客户端要求 TensorFlow Serving 服务器针对给定模型对给定输入图像生成预测。

如果请求的模型尚未提供服务，则会从远程 URL 将其下载到服务器模型所在的文件夹。 （客户这样做）。此时我需要更新model_config并触发服务器重新加载。

此功能似乎存在（基于https://github.com/tensorflow/serving/pull/885 和https://github.com/tensorflow/serving/blob/master/tensorflow_serving/apis/model_service.proto#L22），但我找不到任何有关如何实际使用它的文档。

我本质上是在寻找一个 python 脚本，我可以使用它来触发从客户端重新加载（或者配置服务器以侦听更改并触发重新加载本身）。

Answer 1

如果您使用this answer中描述的方法，请注意，您实际上正在启动多个Tensorflow模型服务器实例而不是单个模型服务器，有效地使服务器竞争资源而不是一起工作以优化尾部延迟。

Answer 2

添加模型到 TF Serving 服务器和现有配置文件 conf_filepath：为新模型使用参数 name、base_path、model_platform。保持原始模型完好无损。

注意与@Karl 的回答有一点不同——使用MergeFrom 而不是CopyFrom

pip install tensorflow-serving-api

import grpc
from google.protobuf import text_format
from tensorflow_serving.apis import model_service_pb2_grpc, model_management_pb2
from tensorflow_serving.config import model_server_config_pb2


def add_model_config(conf_filepath, host, name, base_path, model_platform):
    with open(conf_filepath, 'r+') as f:
        config_ini = f.read()
    channel = grpc.insecure_channel(host)
    stub = model_service_pb2_grpc.ModelServiceStub(channel)
    request = model_management_pb2.ReloadConfigRequest()
    model_server_config = model_server_config_pb2.ModelServerConfig()
    config_list = model_server_config_pb2.ModelConfigList()
    model_server_config = text_format.Parse(text=config_ini, message=model_server_config)

    # Create a config to add to the list of served models
    one_config = config_list.config.add()
    one_config.name = name
    one_config.base_path = base_path
    one_config.model_platform = model_platform

    model_server_config.model_config_list.MergeFrom(config_list)
    request.config.CopyFrom(model_server_config)

    response = stub.HandleReloadConfigRequest(request, 10)
    if response.status.error_code == 0:
        with open(conf_filepath, 'w+') as f:
            f.write(request.config.__str__())
        print("Updated TF Serving conf file")
    else:
        print("Failed to update model_config_list!")
        print(response.status.error_code)
        print(response.status.error_message)

Answer 3

所以我花了很长时间浏览拉取请求，最终找到了一个代码示例。对于下一个和我有同样问题的人，这里有一个如何做到这一点的例子。 （为此，您需要 tensorflow_serving package；pip install tensorflow-serving-api）。

基于此拉取请求（在撰写本文时尚未接受并已关闭，因为它需要审查）：https://github.com/tensorflow/serving/pull/1065

from tensorflow_serving.apis import model_service_pb2_grpc
from tensorflow_serving.apis import model_management_pb2
from tensorflow_serving.config import model_server_config_pb2

import grpc

def add_model_config(host, name, base_path, model_platform):
  channel = grpc.insecure_channel(host) 
  stub = model_service_pb2_grpc.ModelServiceStub(channel)
  request = model_management_pb2.ReloadConfigRequest() 
  model_server_config = model_server_config_pb2.ModelServerConfig()

  #Create a config to add to the list of served models
  config_list = model_server_config_pb2.ModelConfigList()       
  one_config = config_list.config.add()
  one_config.name= name
  one_config.base_path=base_path
  one_config.model_platform=model_platform

  model_server_config.model_config_list.CopyFrom(config_list)

  request.config.CopyFrom(model_server_config)

  print(request.IsInitialized())
  print(request.ListFields())

  response = stub.HandleReloadConfigRequest(request,10)
  if response.status.error_code == 0:
      print("Reload sucessfully")
  else:
      print("Reload failed!")
      print(response.status.error_code)
      print(response.status.error_message)


add_model_config(host="localhost:8500", 
                    name="my_model", 
                    base_path="/models/my_model", 
                    model_platform="tensorflow")