Illegal instruction (core dumped) for BoTSORT
Closed this issue · 4 comments
Search before asking
- I have searched the Yolo Tracking issues and discussions and found no similar questions.
Yolo Tracking Component
Tracking
Bug
Hi, I'm trying to integrate the BoTSORT tracker for tracking in my program. Running the given example (Minimal Reproducible Example) I get the error Illegal instruction (core dumped)
If I swap out the tracker for OCSORT, I don't get the error. What might be the issue?
Environment
- YOLO tracking v10.0.72, torch 2.2.2+cpu (intel core i5 8th gen laptop cpu)
I have also tried torch 1.13.1+cpu
Minimal Reproducible Example
tracker = BoTSORT(
model_weights=None,
device=torch.device(self.device),
fp16=False,
with_reid=False
)
while not self.camera.stopped:
frame = self.camera.read()
r = next(face_model(frame, stream=True, **kwargs))
dets = r.boxes.data.cpu().numpy()
tracked_dets = tracker.update(
dets, frame
) # --> M X (x, y, x, y, id, conf, cls, ind)
Provide the full error please
Provide the full error please
I get this error only, no full traceback. I've tried to following block of code to print traceback of error but it still doesn't print full traceback:
try:
tracked_dets = tracker.update(
dets, frame
) # --> M X (x, y, x, y, id, conf, cls, ind)
except Exception:
print(traceback.format_exc())
Sorry. I cannot help you with this little information. Try:
import traceback
try:
# Simulating your tracking update function call
# Assuming 'tracker.update' is a function that might throw an exception
# Replace 'dets' and 'frame' with actual data that you pass to the function
tracked_dets = tracker.update(dets, frame) # --> M X (x, y, x, y, id, conf, cls, ind)
except Exception as e:
# This should print the error message and the complete traceback
print("An error occurred:", e)
print(traceback.format_exc())
👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.
Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!