YOLO_Object_Tracking_TensorRT Traceback (most recent call last): File "yolov8_deepsort_trt.py", line 145, in <module> main(args) File "yolov8_deepsort_trt.py", line 83, in main bboxes, scores, labels = det_postprocess(data) File "/home/nvidia/gxq_files/YOLOv8_Object_Tracking_TensorRT-main/srcs/models/torch_utils.py", line 63, in det_postprocess assert len(data) == 4 AssertionError ------------------------------------------------------------------- PyCUDA ERROR: The context stack was not empty upon module cleanup. ------------------------------------------------------------------- A context was still active when the context stack was being cleaned up. At this point in our execution, CUDA may already have been deinitialized, so there is no way we can finish cleanly. The program will be aborted now. Use Context.pop() to avoid this problem.有两个错误可以给解答以下吗？

Traceback (most recent call last): File "yolov8_deepsort_trt.py", line 145, in <module> main(args) File "yolov8_deepsort_trt.py", line 83, in main bboxes, scores, labels = det_postprocess(data) File "/home/nvidia/gxq_files/YOLOv8_Object_Tracking_TensorRT-main/srcs/models/torch_utils.py", line 63, in det_postprocess assert len(data) == 4 AssertionError ------------------------------------------------------------------- PyCUDA ERROR: The context stack was not empty upon module cleanup. ------------------------------------------------------------------- A context was still active when the context stack was being cleaned up. At this point in our execution, CUDA may already have been deinitialized, so there is no way we can finish cleanly. The program will be aborted now. Use Context.pop() to avoid this problem.有两个错误可以给解答以下吗？

Open 1204Gin opened this issue 11 months ago • 1 comments

Dec 31 '24 01:12 1204Gin

@1204Gin Can you check your torch is compatative with CUDA ? Please give me your torch and CUDA version ?

Jan 13 '25 09:01 nabang1010