cong / yolov5_deepsort_tensorrt

This repo uses YOLOv5 and DeepSORT to implement object tracking algorithm. Also using TensorRTX to transform model to engine, and deploying all code on the NVIDIA Xavier with TensorRT further.
MIT License
177 stars 35 forks source link

pycuda._driver.LogicError: cuDeviceGet failed: initialization error #3

Closed oussamabousselmi closed 1 year ago

oussamabousselmi commented 3 years ago

when i run demo_trt.py i got this error detector = Detector(engine_file_path) File "/home/radar/Desktop/yolotrt/yolov5_deepsort_tensorrt/detector_trt.py", line 43, in init self.cfx = cuda.Device(0).make_context() pycuda._driver.LogicError: cuDeviceGet failed: initialization error

cong commented 3 years ago

Please carefully check whether the type and dimension information of the input data is correct.

lencm commented 2 years ago

This problem can occur with the engine file provided by the author, and can be solved using your own engine file.