zhewei-mt

> Hi @zhewei-mt, thanks for creating this issue. Did you take a look at the discussion here: #1508? > > Particularly this comment may be helpful: [#1508 (comment)](https://github.com/gradio-app/gradio/issues/1508#issuecomment-1154545730) Already tried...

Thank you for your reply! I upgrade all related version to be consistent with cuda 11.7 and the problem is gone. But at the every last step, another error occurs...

There is something weird happening. I downgrade matplotlib from 3.5.3 to 3.5.2 and still get same error. But when I try using debug mode is vs code, the script seems...

Got you. And is there a way to get the rotation information from the 3d joint position output by your model or do you plan to use rotation information as...

I tried the repo you mentioned. I got the same error when making the result video. Seems that your repo and his are highly related. I tried different version of...

I am having the same problem. I tried same id and cross id, all results seem to have heavy artifact. However, the results video in https://feiiyin.github.io/StyleHEAT/ is more natural. Is...

> Hi I also have the question, did you find a solution, please? Not yet. Waiting for the official reply.

> The first 3 elements of the pose parameters mean the global orientation and the other 69 elements are the joint rotation relative to their parent joints. Both of them...

> Hi @zhewei-mt, That's a good question, I guess the axis angle hasn't been normalized from [here](https://github.com/vchoutas/smplx/blob/4e2a3175c1309abe42b121a41f5c7d78c1935f42/smplx/lbs.py#L317-L318) > > ```python > angle = torch.norm(rot_vecs + 1e-8, dim=1, keepdim=True) > rot_dir...

> You can refer [here](https://github.com/open-mmlab/mmhuman3d/blob/main/mmhuman3d/data/data_converters/h36m.py#L361-L364), where we rectify upside down people in h36m by applying a global rotation ([np.pi, 0, 0]). For example, from my understanding, the output of L_Hip...