Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Crash while recording stats with PilotNet (TF) model on Montreal circuit #392

Closed
nik1806 opened this issue Jul 24, 2022 · 2 comments
Closed

Comments

@nik1806
Copy link
Contributor

nik1806 commented Jul 24, 2022

I got the following output on terminal, after I press stats record button:

[INFO]  Successfully created the data folder ./perfect_bags/lap-simple-circuit.
[INFO]  Successfully created the data folder 20220724-104639.

20: * Completed distance ---> 121.45998400581293
20: * Average speed ---> 7.144704941518407

/root/BehaviorMetrics/behavior_metrics/utils/metrics.py:321: RuntimeWarning: overflow encountered in double_scalars
  min_dists.append(1000 ** min_dist)

20: Unexpected Behavior: Converging to same point
20: * Position deviation MAE ---> inf
20: * Position deviation total error ---> inf
20: Lap not completed
20: * Experiment total simulated time ---> 17.0
20: * Mean network inference time ---> 0.11231924032236075s
20: * Frame rate ---> 49.76470588235294fps

Traceback (most recent call last):
  File "/root/BehaviorMetrics/behavior_metrics/ui/gui/views/toolbar.py", line 255, in mousePressEvent
    self.parent.stop_recording_stats()
  File "/root/BehaviorMetrics/behavior_metrics/ui/gui/views/toolbar.py", line 597, in stop_recording_stats
    self.controller.stop_recording_metrics()
  File "/root/BehaviorMetrics/behavior_metrics/utils/controller.py", line 230, in stop_recording_metrics
    self.experiment_metrics, first_image = self.pilot.calculate_metrics(self.experiment_metrics)
  File "/root/BehaviorMetrics/behavior_metrics/pilot.py", line 233, in calculate_metrics
    brain_iterations_frequency_simulated_time = 1 / mean_brain_iterations_simulated_time
ZeroDivisionError: float division by zero

Aborted (core dumped)
@nik1806
Copy link
Contributor Author

nik1806 commented Jul 24, 2022

I got the same error message when using Dynamic quantized model. With different statistics as:

20: * Completed distance ---> 122.3431087018863
20: * Average speed ---> 8.738793478706164
20: * Position deviation MAE ---> inf
20: * Position deviation total error ---> inf
20: Lap not completed
20: * Experiment total simulated time ---> 14.0
20: * Mean network inference time ---> 0.010323523823680774s
20: * Frame rate ---> 58.92857142857143fps

@nik1806
Copy link
Contributor Author

nik1806 commented Aug 11, 2022

I found the solution. We have to change the PerfectLap argument in the config file, for each circuit. The available options are present in BehaviorMetrics/behavior_metrics/perfect_bags/ directory.

@nik1806 nik1806 closed this as completed Aug 11, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant