search

postech-ami / FastMETRO

[ECCV'22] Official PyTorch Implementation of "Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers"
https://fastmetro.github.io/
MIT License
164 stars 14 forks source link

pretrained models #1

Closed fusichao closed 2 years ago

fusichao commented 2 years ago

Very interested in your work! How to train my own dataset or can you provide some pre training models?

FastMETRO commented 2 years ago

Hello,

Our code is under refactoring. In the meantime, please refer to [Code Snippet (Overall Architecture)] and [Code Snippet (Transformer Encoder-Decoder)] which contains the main framework of our FastMETRO.

The training procedure for FastMETRO is based on METRO. It would be helpful for you to check [INSTALL], [DOWNLOAD] and [EXP] provided by METRO.

We are planning to release our complete code and pre-trained models within a few months.

Thanks for your interest in our work!!

FastMETRO commented 2 years ago

Please reopen this issue if you need more help regarding this.