Hejia Chen

Yes, I also run into this problem in DECA project. ~~~python File "demos/demo_transfer.py", line 131, in main(parser.parse_args()) File "demos/demo_transfer.py", line 84, in main deca.save_obj(os.path.join(savefolder, name, save_type, name + '.obj'), opdict)...

Hi, I think this [issue](https://github.com/TimoBolkart/TF_FLAME/issues/29) in TF-Flame may answer your question.

Hi, I try the latest `Mediapipe == v0.8.8` Face Mesh, it seems that the asymmetrical problem is fixed in the new version. I am working on the Mediapipe replacing OpenFace...

I am planning to train a neural network to predict each AU intensity or binary classification. Before that, couple preprocessing are required, like centralization and normalization, etc.

Thanks for your offer. I will let you know if I run into any problems.

@fire There are plenty public datasets provide AU annotation, like CK+ and DISFA (the dataset used in OpenFace).

> 显示NameError: name 'raw_input' is not defined 使用Python2

You can find the link at https://github.com/uniBruce/Mead/issues/8#issuecomment-966988461.

Hi @filby89 I guess it is possible, meshtalk offers a [code](https://github.com/facebookresearch/meshtalk/blob/main/utils/multiface2meshtalk.py) to convert the multiface to meshtalk topology. BTW, I notice that you are working on the 3D lip-sync task,...

Many thanks for the reply and your assistance. I didn't notice that the pretrained model would be downloaded in another script. https://github.com/radekd91/inferno/blob/53beb5d3d4a9b280f0f9076c59444707e595fbd6/inferno_apps/TalkingHead/download_assets.sh#L50 Closing this issue for now.