About your setting 'mask' equals to 'False'

[Williamongh]

Hi, thanks for sharing! I am wondering that why you set all elements of mask equal to False in pix2seq.py?

        src, mask = features[-1].decompose() 
        assert mask is not None
        mask = torch.zeros_like(mask).bool()   

[hanqiu-hq]

In our previous experiments (with weaker augmentation and shorter training epochs), we found that removing the mask in the transformer leads to slight improvement when changing from relative coordinates to absolute coordinates.