LSTM_Pose_Machines
LSTM_Pose_Machines copied to clipboard
Code repo for "LSTM Pose Machines" (CVPR'18)
Hi, thanks for your great paper and code. I have some questions: 1. How long does it take to pretrain on LEEDS Sport Dataset and MPII Dataset ? And How...
The matlab script is throwing an error: > In JHMDB_PreData (line 102) Error using save Variable 'train' not found. Error in JHMDB_PreData (line 104) save(fileTrain, 'train','-v7.3');
作者您好: 我用pycaffe重现了您的测试代码,测试了一组连续图片,使用time.time()记录(forward())运行时间,平均单帧处理时间大约80ms,我用的GPU型号为单2080TI,cuda10.0, cudnn7.4.2.请问您具体的运行环境是什么?单帧时间大约为多少?
Thanks for your great work! I wonder if I could modify some layers or conv params based on your code? ....feel sorry but not familiar with matlab or caffe.... Also,...
Hi, I have trained your network for first `sub-JHMDB` according to it's default settings, but it 's results on test set is lower than result s of provided weights as...
Hi, the link to Penn_Action.tar.gz on boxcloud is dead. Cheers
@lawy623 作者您好: - 我测试你的代码,出现的下面的错误,提示缺少文件,我也没有找到文件在哪,请问是问题在哪,怎么解决? `Running inference using model LSTM Pose Estimation on sub-JHMDB dataset, Sub1, 7 scales for each sample. load ../dataset/JHMDB/Sub1/test.mat... 错误使用 load 无法读取文件 '../dataset/JHMDB/Sub1/test.mat'。没有此类文件或目录。 出错 run_benchmark_GPU_JHMDB (line 34)...
Hi, Have you changed the image pre-processing of `CPM` for `video` dataset? Would you please share the trained `CPM` weights on `video` dataset for further comparison. Thanks,