ZXin0305
ZXin0305
> Getting 10fps without flip and 7fps with flip on a Titan V. > > Haven't been able to trace the model and preserve size. Also, torchvision op (deform conv2d)...
And what the center heatmap means?Is all the keypoints in an image?Thanks!!!
> Hi, you can find the construction of GT offset map in the lib/dataset/target_generators/target_generators.py. The center heatmap is to find the center points of each person in the image. thanks...
> _MuPoTS_ dataset hello, do you know the camera parameters of the MuPoTS dataset ? Thanks
> Ok, thank you. have you get the camera parameters ?? Thanks .
> hello, have you retrained the model on CMU dataset, and what's the result of the model?? The result after training it on the dataset is so bad by myself.
> Hello,i trained the model on CMU using 3 Nvidia Titan xp cards,and using 200k images.For a complete training process,it takes about half a month....Maybe the computation power is much...
> have you solved this problem??