As we can see from Eq. (3), $\beta = 0$ will render $x^{s→t}$ the same as the original source image $x^s$. On the other hand, when $\beta = 1.0$, the amplitude of $x^s$ will be replaced by that of $x^t$.
But while setting the beta=1, we get almost the original source image back. Also, setting beta=1 should replace all amplitude not just along the smaller axis.
Bug
The border
b
in FDA numpy implementation https://github.com/YanchaoYang/FDA/blob/master/utils/__init__.py#L64 is taken asmin(height, width)*beta
which is not in line with the paper.To quote the paper:
But while setting the beta=1, we get almost the original source image back. Also, setting beta=1 should replace all amplitude not just along the smaller axis.
To Reproduce
Steps to reproduce the behavior:
Output
Expected behavior
The "augmentation" should be maximum at beta=1 not at beta=0.5.