幸运之星正在降临...
点击领取今天的签到奖励!
恭喜!您今天获得了{{mission.data.mission.credit}}积分
我的优惠劵
-
¥优惠劵使用时效:无法使用使用时效:
之前
使用时效:永久有效优惠劵ID:×
没有优惠劵可用!
按照本页教程里的“检查显卡的CUDA Toolkit版本 在Windows里的“运行”,输入cmd,在弹出的命令行界面输入:nvidia-smi,回车,得到下图表格,通过表格右上角的CUDA Version来确定你应该下载的CUDA Toolkit驱动版本” 我看到我的4090对应的CUDA版本是12.0。 “NVIDIA的CUDA驱动下载页面: CUDA Toolkit Archive: https://developer.nvidia.com/cuda-toolkit-archive 安装CUDA Toolkit驱动“中这个英伟达的驱动列表里Latest Release版本就是12.0,可能UVR5还没支持到这个版本的CUDA驱动
MDX-NET算法下的每一个模型都不行
Last Error Received: Error Received while processing "Weekend Boyfriend .mp3": Process Method: MDX-Net If this error persists, please contact the developers with the error details. Traceback Error: " File "inference_MDX.py", line 1692, in main File "inference_MDX.py", line 350, in prediction_setup File "onnxruntimecapionnxruntime_inference_collection.py", line 335, in __init__ File "onnxruntimecapionnxruntime_inference_collection.py", line 381, in _create_inference_session " RuntimeError: "D:a_work1sonnxruntimepythononnxruntime_pybind_state.cc:548 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/reference/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported. " Error Time Stamp [2023-01-17 14:13:21] 可以复制错误LOG了,这个是内容
昨天已经找到,但是错误日志不能复制,看了下大概的内容是和GPU有关,我尝试不使用GPU参与就能运行了。显卡是4090。另外在GIT HUB上下载了最新的5.5版本后执行MDX-NET算法报错是没有了,软件却卡死一会直接奔溃闪退,感觉是不是因为GPU核心版本太新导致的不适配?CUDA驱动下载的对应版本12.0。
Error Received: For raw error details, go to the Error Log tab in the Help Guide. Please address the error and try again. If this error persists, please contact the developers with the error details. Time Elapsed: 00:00:00 我在用MDX-NET算法的时候出现的错误,请问Help Guide在哪里?