我正在尝试根据本教程构建一个程序来预测已经训练过的模型
https://github.com/GoogleCloudPlatform/cloudml-samples/tree/master/flowers
为此,我正在使用Docker和Tensorflow服务跟进本教程:
当我运行基于此示例的客户端时: https://github.com/tensorflow/serving/blob/master/tensorflow_serving/example/inception_client.py
我收到了这个错误:
userml@userml:~/usermodel$ python tensorflow_serving_client.py --server=172.17.0.2:9000 --image=./image5578.jpg
Traceback (most recent call last):
File "tensorflow_serving_client.py", line 87, in <module>
tf.app.run()
File "/home/userml/.local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "tensorflow_serving_client.py", line 46, in main
result = stub.Predict(request, 60.0) # 60 secs timeout
File "/home/userml/.local/lib/python2.7/site-packages/grpc/beta/_client_adaptations.py", line 324, in __call__
self._request_serializer, self._response_deserializer)
File "/home/userml/.local/lib/python2.7/site-packages/grpc/beta/_client_adaptations.py", line 210, in _blocking_unary_unary
raise _abortion_error(rpc_error_call)
grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.INVALID_ARGUMENT, details="input size does not match signature")
我该如何解决这个问题? 我试图找到输入大小,设置'shape [1]'但似乎不起作用。我的模型是否有与客户端不兼容的东西?
非常感谢!