KYANG

Thank you for quick reply! It's very kind of you last two more question: 1. MPJPE of human3.6m is conducted on 14 joints following HMR&SPIN or on 17 joints? 2....

Thanks for quick response! So that is to say, the author's implementation in tensorflow does not match what they described in the paper? ( 440x440 -> 256x256 in the paper)

One more question about the corresponding relation between 2d and 3d joints. Is the 2d input the same as orign repo that includes hip and excludes nose? If so, it's...

Hi, I met the same reproducing issue. Under default training setting, I only got MPJPE=55.6mm. But the disalignment problem you mentioned is not the reason. MPJPE measures the distance all...

> > Here is the wrong annotation example > > Did u figure out the problem now? I met the same problem but worse. The problem comes from error annotation...

@youpJiang I'm not sure whether the drifting error exists in training set, probably none as far as i know. Maybe you can have a try with more accurate 2D detector,...

@youpJiang you are welcome, wish you good result too.

@acmff22 hi, I have the same doubt about dxy. Did you solve it?

@mmichaelzhang Have you resolved this issue? I also observed training loss explosion and encountered performance deterioration for llama2-7b using default llama settings: | Wikitext2 w/o tune | Ptb w/o tune...

Hi all, you can use fine-tuned HRNet at here: [https://github.com/Nicholasli1995/EvoSkeleton](https://github.com/Nicholasli1995/EvoSkeleton) As I have evaluated, it achieves better results than CPN.