Smallwhite999

Results 11 comments of Smallwhite999

> > > 我已经更新了代码, 只需要torchvision和pytorch,不需要安装cupy,nms等第三方代码了,理论上可以在windows下直接跑的 你好,问一下,batch size的话可以设置32,64这些数嘛?可以的话如何修改,麻烦简要解答一下,谢谢

我安装的时候都是按照下面这个安装的: 训练的命令是按照这个操作的: 这些配置完成之后报错是这样的: python -m torch.distributed.launch \ > --nproc_per_node=2 \ > tools/train_net.py \ > --master_port=$((RANDOM+10000)) \ > --config-file configs/MEGA/vid_R_101_c4_MEGA_1x.yaml \ > --motion-specific ***************************************** Setting OMP_NUM_THREADS environment variable for each process...

我再试一下吧,谢谢您的解答! 在2020年7月24日 10:33,Yihong Chen 写道: 你运行命令的时候切换到mega.pytorch这个目录下了吗? — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

并没有 在2020年8月26日 17:20,LauncH 写道: 我再试一下吧,谢谢您的解答! 在2020年7月24日 10:33,Yihong [email protected] 写道: 你运行命令的时候切换到mega.pytorch这个目录下了吗? — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or...

> 数据集太大了,avenue处理完就60G,不好意思! > […](#) > ------------------ 原始邮件 ------------------ 发件人: "LiUzHiAn/hf2vad" ***@***.***>; 发送时间: 2022年3月14日(星期一) 晚上7:53 ***@***.***>; ***@***.******@***.***>; 主题: Re: [LiUzHiAn/hf2vad] 运行pre_process部分报错 (Issue #11) 看起来像是 mmdetection相关的问题,请问你装的mmcv和mmdet的版本是正确的吗? 由于预处理得到的文件比较大,抱歉我没办法直接分享,可能还需要你自己处理一下相关的环境问题。另外,我没有在windows上测试过。 您好,能否将预处理得到的数据分享一下啊?如百度云链接之类的,十分感谢。 — Reply to this email directly, view it...

> `matplotlib.pyplot` would help. If you can, can you share your visualization code? In order to further understand and learn your paper, thank you very much!

> > > pip install pycocotools > > another way: > pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI I have got clone the pycocotools, and the location is correct, but there still has the...

> > > Hellow, Dr. Gong, I'm very interested in your paper on anomaly detection, and I'd like to reproduce the experiment with MNIST and CIFAR-10 data sets. Can you...

> > > > > Hellow, Dr. Gong, I'm very interested in your paper on anomaly detection, and I'd like to reproduce the experiment with MNIST and CIFAR-10 data sets....

> > > Hi, > > May i know how did you train on the Shanghai Tech dataset? > > I trained on the entire dataset end-to-end and got an...