jingli513 / audio2gestures Goto Github PK

Hi, there! I could not find the training and testing data and pre-trained model to have a try. Would you mind releasing the training and testing data and pre-trained model?

Hi, I have got Trinity dataset, how can I retarget the data into SMPLX model using maya? I don't see the official maya version of SMPLX, only the maya version of smpl. Can you provide it?

File "/Users/alexandrrezanov/inworld/gestures/audio2gestures/model.py", line 171, in init
self.smpl_model = SMPLXModel(args.smpl_path)
File "/Users/alexandrrezanov/inworld/gestures/audio2gestures/model.py", line 44, in init
meta_betas, data_struct["shapedirs"]
File "/Users/alexandrrezanov/inworld/gestures/audio2gestures/utils.py", line 659, in blend_shapes
blend_shape = torch.einsum("bl,mkl->bmk", [betas, shape_disps])
File "/Users/alexandrrezanov/opt/anaconda3/envs/audio2gesture3.7/lib/python3.7/site-packages/torch/functional.py", line 297, in einsum
return einsum(equation, *_operands)
File "/Users/alexandrrezanov/opt/anaconda3/envs/audio2gesture3.7/lib/python3.7/site-packages/torch/functional.py", line 299, in einsum
return _VF.einsum(equation, operands) # type: ignore[attr-defined]
RuntimeError: einsum(): operands do not broadcast with remapped shapes [original->remapped]: [1, 20]->[1, 1, 1, 20] [10475, 3, 400]->[1, 10475, 3, 400]

Can you please provide a .pkl file. Or at least some kind of readme

Hi! Could you please give some step by step guidance or point to some resources on how you retarget the trinity speech dataset into SMPLX? Thanks!

Can you share the pretraining model of speech2gesture dataset?

我们试图在linux系统下，VScode平台，使用fbx2hdf.py。
但是，通过官网安装fbx库（https://www.autodesk.com/developer-network/platform-technologies/fbx-sdk-2020-3）后
其运行结果为Segmentation fault (core dumped)
故此，希望向您了解安装fbx的具体方式

Currently I encounter a problem. I import fbx data into Maya. Do I need to use humanik to create a new model? Or author, can you provide smplx model?

你好，非常荣幸能看到这么富有创造力的工作。我在你的代码中看到数据集似乎可以选择speech2gesture，我到目前为止还未获得Trinity数据集许可，我想请问下是否可用speech2gesture数据集进行训练？因为在read me中没有看到相关介绍，所以来打扰你了。

Hi Jing Li,

I've found your article very interesting! I'd like to ask you what method did you use to retarget the data from the Trinity dataset to SMPLX model?

Thank you :)

I have my own fbx model, how should I convert my own fbx model into a pkl file and npz file

Thanks for your work, i want to know how to make _smplx_retargeting.h5 file ?

Hi,

could you share the pre trained models and a script for inference? I would like to try your model on a custom audio!

挺好的一份工作，就是数据处理这块的介绍实在是太少了，想跑起来这份代码太困难了。如果作者愿意把数据处理这一块写得更加的详细，我相信这份代码的收藏量会提高一个量级的。

Hi, Jingli, I have read your excellent article. Are there any plans for open source code recently？
I am very willing to learn your research~