Yuxuan Mu
Yuxuan Mu
In my case, higher disc learning rate while lower disc update frequency might help, in addition to balance reward weights.
Paper name/title: MoMask: Generative Masked Modeling of 3D Human Motions Paper link: https://arxiv.org/abs/2312.00063 Code link: https://github.com/EricGuo5513/momask-codes
Hi, Good question. Intuitively, we select the best fid model on the validation set for the best motion quality. For mask transformer, ideally, we want to consider the metrics comprehensively,...
Hi, Pleased refer to this: https://github.com/EricGuo5513/momask-codes/blob/c7825522ccf259b232aee71418f62724e84e06c3/models/mask_transformer/transformer.py#L184
https://github.com/EricGuo5513/momask-codes/blob/c7825522ccf259b232aee71418f62724e84e06c3/models/mask_transformer/transformer.py#L734
Hi, thanks for your interest! We are happy to figure out the problem together with you. Could you please provide the configures for training (opt file) and testing (scripts) for...
> I just use the provided code and commands without any change. > vq training: [opt.txt](https://github.com/EricGuo5513/momask-codes/files/14352815/opt.txt) > mtrans training: [opt.txt](https://github.com/EricGuo5513/momask-codes/files/14352826/opt.txt) > rtrans training: [opt.txt](https://github.com/EricGuo5513/momask-codes/files/14352831/opt.txt) > vq test: [rvq_nq6.log](https://github.com/EricGuo5513/momask-codes/files/14352903/rvq_nq6.log) > mtrans...
Hi, it's an evaluator checkpoint we use to select model. Specifically, your missing file could be downloaded by ``` gdown --fuzzy https://drive.google.com/file/d/115n1ijntyKDDIZZEuA_aBgffyplNE5az/view?usp=sharing ``` More info could be found in [Get...
Thank you all for your attempts to replicate the results. I just got some time to re-train the masked-transformer and res-transformer using our released code. Here are some results for...
> The same for me, and another confusing problem is the MPJPE of the reconstruction setting on the kit dataset:  > > The command I run is `python eval_t2m_vq.py...