What-If tool could not infer when exporting a model built by estimator.DNNClassifier

• TensorBoard version - built it locally. I cloned the git repository - the latest commit in my local repository is c1e8878b42c16e7018f54613f847b59d357e971e
• TensorFlow version - 1.4
• OS Platform and version - Linux Ubuntu 16.04
• Python version - 3.6

I am trying to use the What-If tool for a model created by using the tf.estimator.DNNClassifier canned estimator. The model was exported and saved. I ran a tensorflow-serving docker and tested is and got back valid results using the following curl command:
curl -d '{"signature_name":"predict","instances":[{.......}]}' -X POST http://192.168.30.15:8501/v1/models/some_model_name:predict

I provided the What-If tool the following definitions:

No infer was done, and I see this message on the TensorBoard output:

/home/guyg/projects/external/tensorboard/bazel-bin/tensorboard/tensorboard.runfiles/org_tensorflow_tensorboard/tensorboard/plugins/interactive_inference/utils/serving/prediction_service_pb2.py:131: DeprecationWarning: beta_create_PredictionService_stub() method is deprecated. This method will be removed in near future versions of TF Serving. Please switch to GA gRPC API in prediction_service_pb2_grpc. 'prediction_service_pb2_grpc.', DeprecationWarning) E0913 15:51:04.739914 Thread-2 _internal.py:87] Error on request: Traceback (most recent call last): File "/home/guyg/.cache/bazel/_bazel_guyg/10aad5f1b9b4fd4ada8c4066e616f3cc/external/org_pocoo_werkzeug/werkzeug/serving.py", line 193, in run_wsgi execute(self.server.app) File "/home/guyg/.cache/bazel/_bazel_guyg/10aad5f1b9b4fd4ada8c4066e616f3cc/external/org_pocoo_werkzeug/werkzeug/serving.py", line 181, in execute application_iter = app(environ, start_response) File "/home/guyg/projects/external/tensorboard/tensorboard/backend/application.py", line 298, in __call__ return self.data_applications[clean_path](environ, start_response) File "/home/guyg/.cache/bazel/_bazel_guyg/10aad5f1b9b4fd4ada8c4066e616f3cc/external/org_pocoo_werkzeug/werkzeug/wrappers.py", line 291, in application return f(*args[:-2] + (request,))(*args[-2:]) File "/home/guyg/projects/external/tensorboard/tensorboard/plugins/interactive_inference/interactive_inference_plugin.py", line 257, in _infer examples_to_infer, serving_bundle) File "/home/guyg/projects/external/tensorboard/tensorboard/plugins/interactive_inference/utils/oss_utils.py", line 136, in call_servo return stub.Classify(request, 30.0) # 30 secs timeout File "/home/guyg/anaconda3/envs/NERD/lib/python3.6/site-packages/grpc/_channel.py", line 487, in __call__ return _end_unary_response_blocking(state, call, False, deadline) File "/home/guyg/anaconda3/envs/NERD/lib/python3.6/site-packages/grpc/_channel.py", line 437, in _end_unary_response_blocking raise _Rendezvous(state, None, None, deadline) grpc._channel._Rendezvous: <_Rendezvous of RPC that terminated with (StatusCode.UNAVAILABLE, Trying to connect an http1.x server)>