无法在Tensorflow服务中即时重新加载配置文件

Question

我正在下面的链接中创建一个脚本，以重新加载动态运行的tensorflow的配置文件。

TensorFlow Serving: Update model_config (add additional models) at runtime

但是，我收到以下错误消息

raise _Rendezvous(state, None, None, deadline)
grpc._channel._Rendezvous: <_Rendezvous of RPC that terminated with:
    status = StatusCode.UNAVAILABLE
    details = "failed to connect to all addresses"
    debug_error_string = " 
{"created":"@1563280495.867330024","description":"Failed to pick subchannel","file":"src/core/ext/filters/client_channel/client_channel.cc","file 
_line":3381,"referenced_errors":[{"created":"@1563280495.867323165","description":"failed to connect to all addresses","file":"src/core/ext/filters/client_channel/lb_policy/pick_first/pick_first.cc","file_line":453,"grpc_status":14}]}"

Answer 1

我通过在使用docker容器并在grpc客户端中使用相同的端口号调用tensorflow服务器的同时分配端口号8500解决了该问题。