makeme-zgz

Results 5 comments of makeme-zgz

模型并行时加载checkpoint导致word embedding size不匹配

请问你成功地进行finetune或者pretrain了吗？@Billijk 我这边通过下载链接得到的checkpoint在加载的时候会有runtime error

Use latent embedding or not?

Thanks so much for the reply! I'm also doing research to make the skill embedding more diversified so that mode collapse can be mitigated and more complex downstream work can...

Unable to achieve good results on Humanoid Reach/Location/Strike tasks

hi, @xbpeng may I ask what was the issue with the pretrained ASE model? and what's being fixed?

How can the output data be converted to bvh format?

Thank you very much for the reply! Quick question on the example data, is it the global or local position of the joints? What would the first entry be like?

How to make the fusion depend on depth and poses only?

@weders Should the pretrained fusion model work with different depth scale and depth map resolution? I'm quite confused with the relationship between the latent feature volume resolution vs the input...