问题描述
我知道一次可以运行多个模型,您可以在配置文件中指定,如 此处.
I know there could be more than one model running at a time, which you can specify in a config file, as explained here.
就我而言,我想用 model_A
、model_B
和 model_C
启动服务器,并在将来添加一个新的任意model_D
无需重启服务器(因为我不想中断模型 A、B 和 C 的服务).
In my case, I want to start the server with model_A
, model_B
and model_C
, and in a future, add a new arbitrary model_D
without restarting the server (since I don't want to interrupt the service for models A, B and C).
有没有办法达到这个要求?
Is there a way to achieve this requirement?
推荐答案
以下提交添加了此功能(并且应该在 TensorFlow Serving 1.7.0 及更高版本中:
The following commit adds this functionality (and should be in TensorFlow Serving 1.7.0 and higher:
https://github.com/tensorflow/serving/commit/78c51b7f7f780860840865c80f78fb7fb7fb7fb9812f5bf
https://github.com/tensorflow/serving/commit/79d3354cd8a408fb981670512d661c2b7e89f5bf
这篇关于如何在 tensorflow 服务中添加新模型的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!