Not able to request the docker server(grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.UNAVAILABLE, details="Connect Failed"))

[Himanshu141]

root@bcc733637737:/serving# bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --port=9000 --model_name=inception --model_base_path=inception-export &> inception_log &
[1] 20

root@bcc733637737:/serving# bazel-bin/tensorflow_serving/example/inception_client --server=localhost:9000 --image=./Xiang_Xiang_panda.jpg

Traceback (most recent call last):
File "/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/tf_serving/tensorflow_serving/example/inception_client.py", line 56, in
tf.app.run()
File "/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/tf_serving/tensorflow_serving/example/inception_client.py", line 51, in main
result = stub.Predict(request, 10.0) # 10 secs timeout
File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 309, in call
self._request_serializer, self._response_deserializer)
File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 195, in _blocking_unary_unary
raise _abortion_error(rpc_error_call)
grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.UNAVAILABLE, details="Connect Failed")
[1]+ Aborted bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --port=9000 --model_name=inception --model_base_path=inception-export &> inception_log

[lilao]

How long did you wait after you ran the tensorflow_model_server and before you ran the inception_client? It is possible that the server hadn't finished startup when you ran the client. Can you wait for some time before running the client? If it still doesn't work, can you get the server log when the client fails?

[visshvesh]

Got same issue.....
grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.UNAVAILABLE, details="Connect Failed"

any solution?

[zihuaweng]

Try this:
#1 Get the container IP address:
docker network inspect bridge | grep IPv4Address
my return : "IPv4Address": "172.17.0.2/16". The IP is 172.17.0.2
#2
bazel-bin/tensorflow_serving/example/inception_client --server=172.17.0.2:9000 --image=/path/to/image.jpg

my system: ubuntu 16.04

[CLIsVeryOK]

root@f685b5d1d3ce:/serving# bazel-bin/tensorflow_serving/example/inception_client --servaer=172.17.0.2:9000 --image=./Xiang_Xiang_panda.jpg
Traceback (most recent call last):
File "/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/tf_serving/tensorflow_serving/example/inception_client.py", line 56, in
tf.app.run()
File "/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/tf_serving/tensorflow_serving/example/inception_client.py", line 51, in main
result = stub.Predict(request, 10.0) # 10 secs timeout
File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 309, in call
self._request_serializer, self._response_deserializer)
File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 195, in _blocking_unary_unary
raise _abortion_error(rpc_error_call)
grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.UNAVAILABLE, details="Connect Failed")

the problem still exist!!! can anyone help me??

[pinkbunny1]

@Himanshu141 @CLIsVeryOK
By looking at inception_log file it requests for an absolute path for model_base_path(Error msg: 'Invalid argument: Expected model inception to have an absolute path or URI'). So change from "--model_base_path=inception-export" to "--model_base_path=//"

For me, I had the inception-model folder in tensorflow folder. So the absolute for my exported model was "/tensorflow-serving/inception-export/". so I did "--model_base_path=/tensorflow-serving/inception-export/"

Command line :

1. bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --port=9000 --model_name=inception --model_base_path=/tensorflow-serving/inception-export/ &> inception_log &

2. (for prediction) bazel-bin/tensorflow_serving/example/inception_client --server=localhost:9000 --image=./Xiang_Xiang_panda.jpg

Output :
outputs {
key: "classes"
value {
dtype: DT_STRING
tensor_shape {
dim {
size: 1
}
dim {
size: 5
}
}
string_val: "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca"
string_val: "indri, indris, Indri indri, Indri brevicaudatus"
string_val: "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens"
string_val: "gibbon, Hylobates lar"
string_val: "sloth bear, Melursus ursinus, Ursus ursinus"
}...

Hope this solves the AbortionError !