WentangChen
WentangChen
Thank you for your quick reply！I would try it later.
> Thank you for your advice!! I've solved the problem mentioned above. There's another question I want to ask, there are still some disconnected roads in the final results. How...
> Sure, you can use pvnet to estimate the initial poses. I am little confused, could you give me some instructions for coding? Thanks very much
> Hi @WentangChen , thanks for your interest in our work. Could you pls try to train with a single GPU and see if the error still exists? hello, I...
 when I run : torchrun --nproc_per_node=4 ./tools/train_net.py --config-file configs/da_faster_rcnn/e2e_da_c2f.yaml , I encounter the above problem. Can you give me some help? looking forward to your reply.
@xinyuliu-jeffrey Thank you for your quick response!  My torch version is 2.1.0, see the pic above
> > 还包括你运行文件的路径，建议改成绝对路径试一下 木南 _**@**_.*** > > […](#) > > ------------------ 原始邮件 ------------------ 发件人: _**@**_._**>; 发送时间: 2024年6月10日(星期一) 下午3:14 收件人: _**@**_.**_>; 抄送: _**@**_._**>; _**@**_.**_>; 主题: Re: [WZMIAOMIAO/deep-learning-for-image-processing] 在云上运行FCN网络的时候使用GPU进行训练会报这个错：FileNotFoundError: [Errno 2] No...
V100是16G的显存吗
请问怎么开多卡训练呢？我设置了 os.environ['CUDA_VISIBLE_DEVICES'] = '4,5,6,7' 和 __C.CONST.DEVICE = '4,5,6,7' 运行脚本python train_pcn.py 一直没反应
不能启动训练，一直卡住：  