Kim Jae Won

안녕하세요 최홍석 연구원님! training dataset관련 질문이 있습니다. 현재 configs 파일안에 여러 yaml 파일들이 있는데요. 논문의 각 table에 대한 성능이 yaml파일에 있는 DB들만 사용한 걸로 이해하면 될까요? 논문에 개제된 성능은 다른...

Why input size is 25 x 6?

6

what a great work! I'm implementing with your code, but I have a question. In your paper, Input is orientations in 6D representation of SMPL body model(24 x 6). When...

Hello! what a great work it is! I'm using your datset, TAD. But I have a question. In your test dataset(val dataset), Normal_218.mp4 is not normal video. There is a...

On your paper, you used Instavariety, posetrack, pennaction, human3.6m, 3dpw, and 3dhp as training dataset. but in config.yaml file, you only used insta, h36m, 3dpw. which one is correct? and...

What a great work! There are some questions related to your work. Can I implemente your code by leveraging torch.distributed.launch without using horovod? And I wonder if the performance in...

what a great work! how to train pennaction dataset?

1

Do you train with pennaction dataset? Could you tell me that, if you do?