uWSGI +Flask+torch Cannot re-initialize CUDA in forked subprocess

用uWSGI +Flask多进程多线程部署你的深度学习应用时，访问会报这样的错

"Cannot re-initialize CUDA in forked subprocess. To use CUDA with "
RuntimeError: Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you must use the 'spawn' start method

查了半天，终于查到怎么使用spawn方法而不是fork

在uWSGI的配置文件中，添加 lazy=true 即可

uWSGI +Flask+torch Cannot re-initialize CUDA in forked subprocess相关推荐

Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you
RuntimeError: Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you ...
cannot re-initialize CUDA in forked subprocess.To use CUDA with multiprocessing,you must use the ...
cannot re-initialize CUDA in forked subprocess.To use CUDA with multiprocessing,you must use the 'sp ...
RuntimeError: Cannot re-initialize CUDA in forked subprocess
问题就在于训练所使用的num_workers数量问题,直接将 num_workers=0 就不会报错了
Torch not compiled with CUDA enabled
Torch not compiled with CUDA enabled 如果没有可用的显卡资源,则检查代码,把调用显卡资源的部分全部去掉即可 https://blog.csdn.net/qq_403 ...
Nginx + uWSGI + flask + socketio 部署解决方案
Nginx + uWSGI + flask + socketio 部署解决方案参考文章: (1)Nginx + uWSGI + flask + socketio 部署解决方案 (2)https:// ...
成功解决raise AssertionError(“Torch not compiled with CUDA enabled“)AssertionError: Torch not compiled
成功解决raise AssertionError("Torch not compiled with CUDA enabled") AssertionError: Torch not ...
AssertionError: Torch not compiled with CUDA enabled到底是什么原因
代码运行报错AssertionError: Torch not compiled with CUDA enabled 但是根据cuda安装显示 cuda是安装成功的这是怎么回事我先进入百度翻译 A ...
Pytorch错误：Torch not compiled with CUDA enabled
一.问题今天跑一个项目代码遇到了一个问题,大致是pytorch和CUDA版本不匹配,然后我就降低pytorch版本,结果1.7中网络不包含我所需的函数,我直接pip install pytorch= ...
AssertionError: Torch not compiled with CUDA enabled 解决方案
报错 Traceback (most recent call last):File "main_pretrain.py", line 250, in <module>m ...
解决 AssertionError Torch not compiled with CUDA enabled
最近在矩池云的的Tesla K80机子上跑MMYOLO,跟着MMYOLO官方文档<自定义数据集标注+训练+测试+部署全流程 >操作到 "2.1.1 软件或者算法辅助" ...

uWSGI +Flask+torch Cannot re-initialize CUDA in forked subprocess

uWSGI +Flask+torch Cannot re-initialize CUDA in forked subprocess相关推荐

最新文章

热门文章