关于RuntimeError: CUDA error: an illegal memory access was encountered的报错求助

[NathanielChenZY]

你好，我在使用trt模型时之前是正常的，但是因为c盘爆红，我不小心清理了虚拟内存，导致帧数暴跌，甚至出些个位数后卡顿然后报错如下，我在网上寻找了办法，依然没有解决，我将虚拟内存开到40个g也没有解决，我的显卡是3070laptop，还请麻烦提供一下帮助，谢谢

[08/22/2024-14:10:44] [TRT] [E] IExecutionContext::executeV2: Error Code 1: Cuda Runtime (an illegal memory access was encountered)
Exception in thread Thread-2 (main_program_loop):
Traceback (most recent call last):
File "D:\aimbot\anaconda\envs\cheater\Lib\threading.py", line 1045, in _bootstrap_inner
self.run()
File "D:\aimbot\anaconda\envs\cheater\Lib\threading.py", line 982, in run
self._target(*self._args, **self.kwargs)
File "D:\aimbot\RookieAI_yolov8\RookieAI_yolov8.py", line 2427, in main_program_loop
results = model.predict(frame, save=False, conf=confidence, half=True, agnostic_nms=True, iou=0.7, classes=[
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\engine\model.py", line 563, in predict
return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\engine\predictor.py", line 168, in call
return list(self.stream_inference(source, model, *args, **kwargs)) # merge list of Result into one
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context
response = gen.send(None)
^^^^^^^^^^^^^^
File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\engine\predictor.py", line 253, in stream_inference
with profilers[1]:
File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\utils\ops.py", line 51, in exit
self.dt = self.time() - self.start # delta-time
^^^^^^^^^^^
File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\utils\ops.py", line 61, in time
torch.cuda.synchronize(self.device)
File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\torch\cuda_init.py", line 801, in synchronize
return torch._C._cuda_synchronize()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

[molanp]

cuda无法访问指定内存，请尝试重新安装cuda或进行冷重启以及系统更新

[1sopropanol]

My account has been stolen and they are sending junk emails or links all over the place. I've changed my password. I'm sorry for what you've received.
1propanol

[Passer1072]

你好，我在使用trt模型时之前是正常的，但是因为c盘爆红，我不小心清理了虚拟内存，导致帧数暴跌，甚至出些个位数后卡顿然后报错如下，我在网上寻找了办法，依然没有解决，我将虚拟内存开到40个g也没有解决，我的显卡是3070laptop，还请麻烦提供一下帮助，谢谢

[08/22/2024-14:10:44] [TRT] [E] IExecutionContext::executeV2: Error Code 1: Cuda Runtime (an illegal memory access was encountered) Exception in thread Thread-2 (main_program_loop): Traceback (most recent call last): File "D:\aimbot\anaconda\envs\cheater\Lib\threading.py", line 1045, in _bootstrap_inner self.run() File "D:\aimbot\anaconda\envs\cheater\Lib\threading.py", line 982, in run self._target(*self.args, **self.kwargs) File "D:\aimbot\RookieAI_yolov8\RookieAI_yolov8.py", line 2427, in main_program_loop results = model.predict(frame, save=False, conf=confidence, half=True, agnostic_nms=True, iou=0.7, classes=[ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\engine\model.py", line 563, in predict return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\engine\predictor.py", line 168, in call return list(self.stream_inference(source, model, *args, **kwargs)) # merge list of Result into one ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context response = gen.send(None) ^^^^^^^^^^^^^^ File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\engine\predictor.py", line 253, in stream_inference with profilers[1]: File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\utils\ops.py", line 51, in exit self.dt = self.time() - self.start # delta-time ^^^^^^^^^^^ File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\ultralytics\utils\ops.py", line 61, in time torch.cuda.synchronize(self.device) File "D:\aimbot\anaconda\envs\cheater\Lib\site-packages\torch\cuda__init.py", line 801, in synchronize return torch._C._cuda_synchronize() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: CUDA error: an illegal memory access was encountered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

尝试重新安装CUDA环境，如果不起作用建议直接重装系统或采用双系统。