Zhixing Zhang

Thanks for your excellent work. As stated in your paper, your encoder generates styles code in w space. However, in your code, I think you use z space instead. Maybe...

@xsacha Thanks for your interest in our work. The `get_embedding` function for the dataset is implemented [here](https://github.com/xiaofeng94/VL-PLM/blob/d41f8be66335a3d2edcd55c355a5108e89a28fb3/VL_PLM/data/datasets/coco.py#L205-L217). So if you directly change the label space to a subset of the...