Getting following error from my python grpc client when trying to connect to the tf-serving server:
<_Rendezvous of RPC that terminated with:
status = StatusCode.FAILED_PRECONDITION
details = "Serving signature key "tensorflow/serving/predict" not found."
debug_error_string = "{"created":"@1540559424.720048798","description":"Error received from peer","file":"src/core/lib/surface/call.cc","file_line":1099,"grpc_message":"Serving signature key "tensorflow/serving/predict" not found.","grpc_status":9}"
>
I believe this means when I build the servables the method name was wrong. But I see that in my servable model builder script I am using the correct name.
prediction_signature = tf.saved_model.signature_def_utils.build_signature_def(
inputs=input_signature,
outputs=output_signature,
method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME)
builder = saved_model_builder.SavedModelBuilder(os.path.join(output_path, str(version_number)))
What can be the reason for this error at client side?