Duckietown Challenges Home Challenges Submissions

Submission 2355

Submission2355
Competingyes
Challengeaido2_LFV_r3-v4-z2
UserAndrea Censi 🇨🇭
Date submitted
Last status update
Completecomplete
DetailsEvaluation is complete.
Sisters
Result💔
Jobsstep1-simulation: 17219
Next
User labelbaseline-IL-logs-tensorflow
Admin priority50
Blessingn/a
User priority50

The highlights are available only to the owner and the admins.

Evaluation jobs for this submission

See previous jobs for previous versions of challenges
Job IDstepstatusup to datedate starteddate completeddurationmessage
17219step1-simulationfailedyes0:01:09
InvalidSubmission: T [...]
InvalidSubmission:
Traceback (most recent call last):
  File "experiment_manager.py", line 285, in run_episode
    r: MsgReceived = agent.write_topic_and_expect('get_commands', expect='commands')
  File "/project/src/zuper-nodes/src/zuper_nodes_wrapper/wrapper_outside.py", line 92, in write_topic_and_expect
    ob: MsgReceived = self.read_one(expect_topic=expect, timeout=timeout)
  File "/project/src/zuper-nodes/src/zuper_nodes_wrapper/wrapper_outside.py", line 173, in read_one
    nickname=self.nickname)
  File "/project/src/zuper-nodes/src/zuper_nodes_wrapper/wrapper_outside.py", line 254, in read_reply
    others = read_until_over(fpout, timeout=timeout, nickname=nickname)
  File "/project/src/zuper-nodes/src/zuper_nodes_wrapper/wrapper_outside.py", line 282, in read_until_over
    raise RemoteNodeAborted(m)
zuper_nodes.structures.RemoteNodeAborted: External node "agent" aborted:

error in agent |Exception while handling a message on topic "get_commands".
               |
               || Traceback (most recent call last):
               ||   File "/project/src/zuper-nodes/src/zuper_nodes_wrapper/wrapper.py", line 274, in loop
               ||     handle_message_node(parsed, receiver0, context0)
               ||   File "/project/src/zuper-nodes/src/zuper_nodes_wrapper/wrapper.py", line 428, in handle_message_node
               ||     call_if_fun_exists(agent, expect_fn, data=ob, context=context, timing=timing)
               ||   File "/project/src/zuper-nodes/src/zuper_nodes_wrapper/utils.py", line 18, in call_if_fun_exists
               ||     f(**kwargs)
               ||   File "imitation_agent.py", line 66, in on_received_get_commands
               ||     pwm_left, pwm_right = self.compute_action(self.config.current_image)
               ||   File "imitation_agent.py", line 41, in compute_action
               ||     graph = load_graph(frozen_model_filename)
               ||   File "/project/graph_utils.py", line 8, in load_graph
               ||     graph_def.ParseFromString(f.read())
               ||   File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/lib/io/file_io.py", line 125, in read
               ||     self._preread_check()
               ||   File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/lib/io/file_io.py", line 85, in _preread_check
               ||     compat.as_bytes(self.__name), 1024 * 512, status)
               ||   File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/errors_impl.py", line 528, in __exit__
               ||     c_api.TF_GetCode(self.status.status))
               || tensorflow.python.framework.errors_impl.NotFoundError: frozen_graph.pb; No such file or directory
               ||

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/project/src/duckietown-challenges/src/duckietown_challenges/cie_concrete.py", line 610, in scoring_context
    yield cie
  File "experiment_manager.py", line 426, in <module>
    wrap(cie)
  File "experiment_manager.py", line 415, in wrap
    main(cie, logdir, attempts)
  File "experiment_manager.py", line 128, in main
    physics_dt=config.physics_dt)
  File "experiment_manager.py", line 289, in run_episode
    raise dc.InvalidSubmission(msg) from e
duckietown_challenges.exceptions.InvalidSubmission: Trouble with communication to the agent.
Artefacts hidden. If you are the author, please login using the top-right link or use the dashboard.
No reset possible