Zhenlin Xu comments

Repositories
Issues
Comments

Results 2 comments of


                                            Zhenlin Xu

RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the sam

I also met this issue. It is weird that the issue arises in some function but not others that all calls the same visual encoder `self.ln_vision(self.visual_encoder(image))`. Does anyone know why?

The code loss function of the segmentation part does not match the paper

@Hongben-fba Thanks for your interests. The current released version only has the pure segmentation model training. The registration and segmentation+registration code is not released yet.