Open 1623021453 opened 8 months ago
trt模型是用本工程中的代码转的,请问有人知道是什么原因吗?困扰了我好久
Check whether your tensorRT version is compatible with the cuda version.
是适配的,我的cuda版本是11.4,tensorrt的版本8.2 8.4 8.6都有试过,都是会直接中断
---原始邮件--- 发件人: "Kai Chun, @.> 发送时间: 2024年1月17日(周三) 下午2:12 收件人: @.>; 抄送: @.**@.>; 主题: Re: [jason-li-831202/Vehicle-CV-ADAS] 运行demo.py报错 (Issue #18)
Check whether your tensorRT version is compatible with the cuda version.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
我也是运行了demo.py报错
~/catkin_ws/src/Vehicle-CV-ADAS$ python3 demo.py
/usr/lib/python3/dist-packages/scipy/init.py:146: UserWarning: A NumPy version >=1.17.3 and <1.25.0 is required for this version of SciPy (detected version 1.26.4
warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
Traceback (most recent call last):
File "/home/pixbus/catkin_ws/src/Vehicle-CV-ADAS/ObjectDetector/yoloDetector.py", line 9, in
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/pixbus/catkin_ws/src/Vehicle-CV-ADAS/demo.py", line 7, in
这是我的cuda版本:
nvidia-smi
Sat Apr 20 15:21:19 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 545.23.08 Driver Version: 545.23.08 CUDA Version: 12.3 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 3060 On | 00000000:01:00.0 On | N/A |
| 30% 34C P8 14W / 170W | 131MiB / 12288MiB | 1% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | 0 N/A N/A 1395 G /usr/lib/xorg/Xorg 78MiB | | 0 N/A N/A 1700 G /usr/bin/gnome-shell 23MiB | | 0 N/A N/A 10782 G ...seed-version=20240419-130118.436000 18MiB | +---------------------------------------------------------------------------------------+
Try commenting out the three lines above.
我注释了,最后我得到这个结果,我确保我已经安装了,tensorrt
我可以正常运行demo.py了,我把cuda从11.4换成11.3后可以正常运行了,感谢作者的分享
我注释了,最后我得到这个结果,我确保我已经安装了,tensorrt
作者的代码是在windows下运行的,你是在ubuntu下运行的吗?
运行onnx模型可以正常运行,运行trt模型,直接中断,输出如下 [2024-01-17 10:25:43] [INFO] [Pycuda] Cuda Version: (11, 4, 0) [2024-01-17 10:25:43] [INFO] [Driver] Cuda Version: 12020 [2024-01-17 10:25:43] [INFO] ---------------------------------------- [2024-01-17 10:25:43] [INFO] UfldDetector Model Type : UFLDV2_CULANE