search

EricGuo5513 / momask-codes

Official implementation of "MoMask: Generative Masked Modeling of 3D Human Motions (CVPR2024)"
https://ericguo5513.github.io/momask/
MIT License
689 stars 56 forks source link

A mean and std computation and use question #33

Open RobinWitch opened 3 months ago

RobinWitch commented 3 months ago

Hello, what a good work! While I have a question when I retrain rvqvae, it quite diffuse me a lot. Why in this place we need to recalculate std? https://github.com/EricGuo5513/momask-codes/blob/d4d34120ea01e3fda09944c3c030e8befe8c19e2/data/t2m_dataset.py#L41-L68

EricGuo5513 commented 3 months ago

Hi, here we are calculating group-based std and also amplifying the importance of certain motion features.

On Wed, Mar 27, 2024 at 9:13 PM RobinWitch @.***> wrote:

Hello, what a good work! While I have a question when I retrain rvqvae, it quite diffuse me a lot. Why in this place we need to recalculate std?

https://github.com/EricGuo5513/momask-codes/blob/d4d34120ea01e3fda09944c3c030e8befe8c19e2/data/t2m_dataset.py#L43

— Reply to this email directly, view it on GitHub https://github.com/EricGuo5513/momask-codes/issues/33, or unsubscribe https://github.com/notifications/unsubscribe-auth/AKRYNBYUESAOME5XNSJEQJ3Y2ODF3AVCNFSM6AAAAABFMAUNMKVHI2DSMVQWIX3LMV43ASLTON2WKOZSGIYTEMRWGIZTIMQ . You are receiving this because you are subscribed to this thread.Message ID: @.***>

RobinWitch commented 3 months ago

In intuitive, I think amplifying the importance of certain motion features we should plus opt.feat_bias instead of dividing? The default value of opt.feat_bias is 5.