小白求助这是facefusion2.3的cuda的错误，因为不用就正常了，这是什么错误怎么解决，第一次运行的适合还没有这种错误

最新推荐文章于 2024-07-24 15:52:26 发布
最新推荐文章于 2024-07-24 15:52:26 发布
阅读量1.8k 收藏 16
点赞数 14
文章标签： 数据库 网络
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/kduehf/article/details/136534229
版权


Running on local URL:  http://127.0.0.1:7860
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
  File "asyncio\events.py", line 80, in _run
  File "asyncio\proactor_events.py", line 162, in _call_connection_lost
ConnectionResetError: [WinError 10054] 远程主机强迫关闭了一个现有的连接。
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
  File "asyncio\events.py", line 80, in _run
  File "asyncio\proactor_events.py", line 162, in _call_connection_lost
ConnectionResetError: [WinError 10054] 远程主机强迫关闭了一个现有的连接。
2024-03-07 14:48:27.0008048 [E:onnxruntime:, sequential_executor.cc:514 onnxruntime::ExecuteKernel] Non-zero status code returned while running Conv node. Name:'/conv_body_up.5/skip/Conv' Status Message: D:\a\_work\1\s\onnxruntime\core\framework\bfc_arena.cc:376 onnxruntime::BFCArena::AllocateRawInternal Failed to allocate memory for requested buffer of size 134217728

Traceback (most recent call last):
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\routes.py", line 534, in predict
    output = await route_utils.call_process_api(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\route_utils.py", line 226, in call_process_api
    output = await app.get_blocks().process_api(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\blocks.py", line 1550, in process_api
    result = await self.call_function(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\blocks.py", line 1185, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\anyio\_backends\_asyncio.py", line 2134, in run_sync_in_worker_thread
    return await future
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\utils.py", line 661, in wrapper
    response = f(*args, **kwargs)
  File "D:\Program Files (x86)\facefusion\facefusion\uis\components\preview.py", line 150, in update_preview_image
    conditional_append_reference_faces()
  File "D:\Program Files (x86)\facefusion\facefusion\core.py", line 244, in conditional_append_reference_faces
    abstract_reference_frame = frame_processor_module.get_reference_frame(source_face, reference_face, reference_frame)
  File "D:\Program Files (x86)\facefusion\facefusion\processors\frame\modules\face_enhancer.py", line 229, in get_reference_frame
    return enhance_face(target_face, temp_vision_frame)
  File "D:\Program Files (x86)\facefusion\facefusion\processors\frame\modules\face_enhancer.py", line 183, in enhance_face
    crop_vision_frame = apply_enhance(crop_vision_frame)
  File "D:\Program Files (x86)\facefusion\facefusion\processors\frame\modules\face_enhancer.py", line 202, in apply_enhance
    crop_vision_frame = frame_processor.run(None, frame_processor_inputs)[0][0]
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 220, in run
    return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Conv node. Name:'/conv_body_up.5/skip/Conv' Status Message: D:\a\_work\1\s\onnxruntime\core\framework\bfc_arena.cc:376 onnxruntime::BFCArena::AllocateRawInternal Failed to allocate memory for requested buffer of size 134217728

2024-03-07 14:48:27.1474147 [E:onnxruntime:, sequential_executor.cc:514 onnxruntime::ExecuteKernel] Non-zero status code returned while running Resize node. Name:'/Resize_12' Status Message: D:\a\_work\1\s\onnxruntime\core\framework\bfc_arena.cc:376 onnxruntime::BFCArena::AllocateRawInternal Failed to allocate memory for requested buffer of size 134217728

Traceback (most recent call last):
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\routes.py", line 534, in predict
    output = await route_utils.call_process_api(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\route_utils.py", line 226, in call_process_api
    output = await app.get_blocks().process_api(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\blocks.py", line 1550, in process_api
    result = await self.call_function(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\blocks.py", line 1185, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\anyio\_backends\_asyncio.py", line 2134, in run_sync_in_worker_thread
    return await future
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\utils.py", line 661, in wrapper
    response = f(*args, **kwargs)
  File "D:\Program Files (x86)\facefusion\facefusion\uis\components\preview.py", line 150, in update_preview_image
    conditional_append_reference_faces()
  File "D:\Program Files (x86)\facefusion\facefusion\core.py", line 244, in conditional_append_reference_faces
    abstract_reference_frame = frame_processor_module.get_reference_frame(source_face, reference_face, reference_frame)
  File "D:\Program Files (x86)\facefusion\facefusion\processors\frame\modules\face_enhancer.py", line 229, in get_reference_frame
    return enhance_face(target_face, temp_vision_frame)
  File "D:\Program Files (x86)\facefusion\facefusion\processors\frame\modules\face_enhancer.py", line 183, in enhance_face
    crop_vision_frame = apply_enhance(crop_vision_frame)
  File "D:\Program Files (x86)\facefusion\facefusion\processors\frame\modules\face_enhancer.py", line 202, in apply_enhance
    crop_vision_frame = frame_processor.run(None, frame_processor_inputs)[0][0]
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 220, in run
    return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Resize node. Name:'/Resize_12' Status Message: D:\a\_work\1\s\onnxruntime\core\framework\bfc_arena.cc:376 onnxruntime::BFCArena::AllocateRawInternal Failed to allocate memory for requested buffer of size 134217728

Analysing:   0%|                                                                           | 0/5727 [00:00<?, ?frame/s]2024-03-07 14:48:29.8507933 [E:onnxruntime:, inference_session.cc:1799 onnxruntime::InferenceSession::Initialize::<lambda_197d3b7975b9bacd9690b0adb4064ca2>::operator ()] Exception during initialization: D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUBLAS failure 3: CUBLAS_STATUS_ALLOC_FAILED ; GPU=0 ; hostname=BC-20240108FWYD ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_execution_provider.cc ; line=168 ; expr=cublasCreate(&cublas_handle_);


Analysing:   0%|                                                                           | 0/5727 [00:00<?, ?frame/s]
Traceback (most recent call last):
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\routes.py", line 534, in predict
    output = await route_utils.call_process_api(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\route_utils.py", line 226, in call_process_api
    output = await app.get_blocks().process_api(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\blocks.py", line 1550, in process_api
    result = await self.call_function(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\blocks.py", line 1185, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\anyio\_backends\_asyncio.py", line 2134, in run_sync_in_worker_thread
    return await future
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\gradio\utils.py", line 661, in wrapper
    response = f(*args, **kwargs)
  File "D:\Program Files (x86)\facefusion\facefusion\uis\components\output.py", line 53, in start
    conditional_process()
  File "D:\Program Files (x86)\facefusion\facefusion\core.py", line 229, in conditional_process
    process_video(start_time)
  File "D:\Program Files (x86)\facefusion\facefusion\core.py", line 274, in process_video
    if analyse_video(facefusion.globals.target_path, facefusion.globals.trim_frame_start, facefusion.globals.trim_frame_end):
  File "D:\Program Files (x86)\facefusion\facefusion\content_analyser.py", line 100, in analyse_video
    if analyse_frame(frame):
  File "D:\Program Files (x86)\facefusion\facefusion\content_analyser.py", line 73, in analyse_frame
    content_analyser = get_content_analyser()
  File "D:\Program Files (x86)\facefusion\facefusion\content_analyser.py", line 38, in get_content_analyser
    CONTENT_ANALYSER = onnxruntime.InferenceSession(model_path, providers = apply_execution_provider_options(facefusion.globals.execution_providers))
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 419, in __init__
    self._create_inference_session(providers, provider_options, disabled_optimizers)
  File "D:\Program Files (x86)\facefusion\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 463, in _create_inference_session
    sess.initialize_session(providers, provider_options, disabled_optimizers)
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUBLAS failure 3: CUBLAS_STATUS_ALLOC_FAILED ; GPU=0 ; hostname=BC-20240108FWYD ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_execution_provider.cc ; line=168 ; expr=cublasCreate(&cublas_handle_);

kduehf
关注
解决 [ONNXRuntimeError] : 1 : FAIL Non-zero status code returned
05-16
pytorch转onnx模型后，对onnx模型进行runtime时提示以下错误，具体细节如下： onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running FusedConv node. Name:'Conv_461_Add_463_Relu_464' Status Message: CUDNN error executing cudnnSetTensorNdDescriptor(tensor_, dataType, static_cast<int>(rank), dims.data(), strides.data())。 pdf文件中是对该错误的解决思路。
FaceFusion常见问题
嘟嘟的博客
03-30 2743
如果都没有，那么是视频元数据的问题，换个视频试下。如果非要用指定视频，将视频放到剪映中重新导出mp4再进入facefusion换脸。当你的系统名不是中文，但是遇到了这个问题，检查下你的图片/视频的名字是不是有中文。将解压后的文件夹删除，下载BandiZip解压软件重新解压。出现这个问题，首先排除下是不是你上传的图片或者视频文件名中有中文！解决方法：图片/视频路径或者文件名改名。根据这篇文章修改下C盘的文件夹名。这是由于系统名是中文导致的。图片和视频路径中是否有中文！通常发生在视频处理完成后。
部署facefusion模型可能遇到的错误
Iverson_TJ的博客
03-20 823
在安装python依赖时如果遇到这个错误。可以尝试使用这个命令安装。
FaceFusion2.61安装及配置使用CUDA+cudnn
最新发布
liangma的专栏
07-24 1804
cuda12.5+cudnn9.2+onnxruntime-gpu1.18.1，可以支撑FaceFusion2.61
FaceFusion 低版本CUDA实测
weixin_45052460的博客
04-02 849
经本人实测，以下配置可以运行facefusionCUDA加速。安装1.12 onnx和8.2.2.26 cuDNN。需补安装zlib123。运行API：11.4。
RuntimeError: Event loop is closed，py3.8协程问题报错解决方法
Aasee的博客
02-21 1520
将asyncio.run(get_url(main())) 改为asyncio.get_event_loop().run_until_complete(main()) 总结来说就是aiohttp 内部使用了 _ProactorBasePipeTransport ，程序退出释放内存时自动调用其 _ProactorBasePipeTransport.__del__方法导致二次关闭事件循环。一般的协程程序是不会使用_ProactorBasePipeTransport 的，所以asyncio.run() 还是可以
python协程：RuntimeError: Event loop is closed解决办法
weixin_46830352的博客
11-17 9346
在学习协程时，用asyncio.run()运行会出现一下RuntimeError: Event loop is closed，如下 解决办法：将 asyncio.run(main())替换为下面两行 loop = asyncio.get_event_loop() loop.run_until_complete(main()) 总而言之是asyncio.run()会自动关闭循环,并且调用_ProactorBasePipeTransport.__del__报错, 而asyncio.run_un.
Ubuntu20.04安装CUDA、cuDNN、onnxruntime、TensorRT
weixin_42156097的博客
10-14 5286
Ubuntu20.04系统安装CUDA、cuDNN、onnxruntime、TensorRT
cuda-11.2.0-460.27.04-linux.run cuda安装包 亲测可用 总共四个 这个是第一个
05-10
cuda-11.2.0-460.27.04-linux.run cuda安装包 亲测可用 总共四个 这个是第一个cuda-11.2.0-460.27.04-linux.run cuda安装包 亲测可用 总共四个 这个是第一个cuda-11.2.0-460.27.04-linux.run cuda安装包 亲测可用 ...
cuda-11.2.0-460.27.04-linux.run cuda安装包 亲测可用 总共四个 这个是第三个
05-10
cuda-11.2.0-460.27.04-linux.run cuda安装包 亲测可用 总共四个 这个是第三个cuda-11.2.0-460.27.04-linux.run cuda安装包 亲测可用 总共四个 这个是第三个cuda-11.2.0-460.27.04-linux.run cuda安装包 亲测可用 ...
Destruction-CUDA-Depreciated：这是我使用CUDA的引擎的一些早期代码
02-16
4. **错误处理和调试**：CUDA编程中的错误处理非常重要，早期的代码可能使用了`cudaGetLastError`和`cudaError_t`进行错误检查，而在现代CUDA编程中，通常推荐使用`cudaDeviceSynchronize`配合`cudaError_t`来检测和...
HAMC:这是基于QC-MDPC代码的基于CUDA的McEliece密码系统的实现
04-14
基于CUDA的实现 如何构建和运行： 首先构建软件： $ mkdir -p build_dir && cd build_dir $ cmake ../src/ $ make 然后运行测试程序： $ ./hamc -c -a test -n 2 -p 500 -t 10 -w 30 基于CPU的执行： HAMC/...
docker nvidia-smi Failed to initialize NVML: Driver/library version mismatch RuntimeError: cuda_call
hknaruto的专栏
06-26 597
x86_64 ubuntu20.04操作系统上制作的docker，在深度20.8上运行测试报错python报错。
OnnxRunTime遇到FAIL : Non-zero status code returned while running BatchNormalization node.
hjxu2016的博客
10-29 1万+
遇到FAIL : Non-zero status code returned while running BatchNormalization node. 跑onnxruntime时，发现显卡没有用到 pip install onnxruntime默认是cpu版本的，如何使用gpu版本呢？ 卸载cpu的，再安装GPU的、 我是这么做的。 用rt.get_device()查看是否能够使用GPU版本 import onnxruntime as rt rt.get_device() 安装GPU版本的onnxru
笨笨小白求助大神，GPT-SoVITS求助
weixin_51581309的博客
06-13 315
不会弄了，按照视频弄得，结果整不出声音，求助大神。
开源人脸融合 AI换脸工具-FaceFusion
爱琳先生的博客
08-31 8130
此钩子在程序启动时调用。此挂钩在渲染之前调用。呈现布局时调用此挂钩。调用此挂钩以添加事件侦听器。
【超详细教程】云端部署AI换脸开源工具FaceFusion（内附超详细的AI工具使用指南）
热门推荐
Little_Carter的博客
02-02 1万+
FaceFusion是一款开源的AI换脸工具，它能够将一个人的脸部特征替换到另一个人的身体上，实现面部表情和动作的同步。这种技术可以用于制作电影、游戏、社交媒体等多种领域，带来丰富的娱乐和创意效果。
ONNXRUNTIME_EXCEPTION : Non-zero status code returned while running Where node. Name:‘Where‘
andrewchen1985的博客
06-17 8304
遇到此类错误，如：onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Non-zero status code returned while running Gather node. Name:'Gather_4445' Status Message: indices element out of data bounds, idx=8 must be
运行python时，报了这段错误，这是什么意思：CUDA error: device-side assert triggered
07-12
当在运行Python程序时出现"CUDA error: device-side assert triggered"错误时，这通常表示在CUDA设备的代码中触发了设备侧断言（device-side assert）。CUDA是用于在NVIDIA GPU上进行并行计算的平台和编程模型。 设备侧断言通常是由于程序中的错误导致的，可能是由于不正确的内存访问、越界访问或其他CUDA相关操作的问题。这种错误通常是由CUDA运行时系统检测到的，并且会导致程序中止。 要解决这个问题，你可以尝试以下步骤： 1. 确保你的CUDA驱动程序和CUDA工具包已正确安装，并且与你的GPU兼容。 2. 检查你的代码是否存在错误，例如内存越界、未初始化变量等。 3. 确保你正在使用支持的CUDA版本，并且你的代码与所使用的CUDA版本兼容。 4. 使用调试工具（如NVIDIA Nsight）对代码进行调试，以确定出错的具体位置和原因。 5. 查阅相关文档、论坛或社区，寻找类似问题的解决方案或其他用户的经验。 请注意，这只是一般性的建议，具体解决方法可能因你的代码和环境而异。
评论 4
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值