Question

我在keras中构建了一个分段模型，并希望在tensorflow服务中运行该模型。目前我能够导出模型并运行模型服务器，但是当我运行client.py文件时输出太大了。错误是：

  File "/home/.../serving/bazel-bin/tensorflow_serving/car_mask/mask_client.runfiles/tf_serving/tensorflow_serving/car_mask/mask_client.py", line 47, in <module>
    result = stub.Predict(request, 10.0)
  File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 310, in __call__
    self._request_serializer, self._response_deserializer)
  File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 196, in _blocking_unary_unary
    raise _abortion_error(rpc_error_call)
grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.RESOURCE_EXHAUSTED, details="Received message larger than max (4194349 vs. 4194304)")

如何解决这个问题？有没有办法添加任何grpc选项来增加client.py文件中的邮件大小？谢谢！

Answer 1

你可以试试这个：

import grpc.beta.implementations
from grpc._cython import cygrpc

def insecure_channel(host, port):
        channel = grpc.insecure_channel(
            target=host if port is None else '%s:%d' % (host, port),
            options=[(cygrpc.ChannelArgKey.max_send_message_length, -1),
                     (cygrpc.ChannelArgKey.max_receive_message_length, -1)])
        return grpc.beta.implementations.Channel(channel)

来自here

grpc.framework.interfaces.face.face.AbortionError：AbortionError（code = StatusCode.RESOURCE_EXHAUSTED，details =“收到的消息大于最大值

1 个答案: