sdf0615

icon location Beijing China icon location Beihang University, playing with code

Results 14 comments of sdf0615

Duke video dataset cannot be accessed

@layumi Dear Zhedong, we cannot visit the website http://vision.cs.duke.edu/DukeMTMC/data/misc/DukeMTMC-VideoReID.zip could you help me solve the problem? Thanks

可以转换为arkit 52个blandshape吗？

I also meet the problem

demo code

Dear @meliketoy, Thanks for your kind help, could you please tell me more about the HOI detection demo process? I am now just trying to use the pretrained model to...

demo code

Dear @meliketoy, I find that the VCOCO's action labels have 29 classes, while the pair actions only have 26 classes, could you tell me to remove which 3 classes?

Pretrained model

Thanks for your quick reply.

The sun model is not available

Hi@alexgkendall， why the sun dataset the two models are the same link? Segnet model file: segnet_sun.prototxt weights: [http://mi.eng.cam.ac.uk/~agk34/resources/SegNet/segnet_sun.caffemodel] Segnet model file: bayesian_segnet_sun.prototxt weights: [http://mi.eng.cam.ac.uk/~agk34/resources/SegNet/segnet_sun.caffemodel]

mAP extremely low when testing on Caltech

@msha096 @rainofmine Thanks. Could you please share the test code?

更换数据集（human3.6m）去重新训练retargeting 模型

@xinzi2018 , hi, how did you convert the human3.6m motion to bvh, could you please make your code public available? thanks very much

更换数据集（human3.6m）去重新训练retargeting 模型

@xinzi2018 Thank you very much

更换数据集（human3.6m）去重新训练retargeting 模型

> 我将human3.6m部分bvh数据集作为groupA , 然后您提供的Mixamo数据集中的***_m.bvh作为训练集中的groupB，训练结束后使用human3.6m中的另一部分作为测试集去测试，结果是正确的。但是我再使用项目[VideoTo3dPoseAndBvh](https://github.com/HW140701/VideoTo3dPoseAndBvh)将视频中提取出来的bvh （观察过该bvh结构和human3.6m的相同）作为输入时，retarget的结果就是错乱的动作，可否有可以提供的思路去解决的？ @xinzi2018 ，大佬解决了这个问题了吗？