New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Question on alignment.py #7
Comments
It is for even-size kernels. Currently, the alignment only supports ever-sized kerkers. For example, when kernel size is 6, this gives a local mesh grid of [-2.5, -1.5, -0.5, 0.5, 1.5, 2.5]^2. |
But if you add |
Yes, or you may also modify the range of p_0 to [0, h-1]. |
Ok, Thanks for the answer! |
Hi,
I have a question on alignment.py in which affine transformation is patch-wisely applied. I am not an expert on deformable convolution, which I believe the code is based on, so please be patient with my question ;)
In
def _get_p_n(...)
, why do you subtract 0.5 and add 0.6 to the range? Is it for the even-size kernel?In
def _get_p(...)
Why do you add(self.kernel_size-1)//2+0.5
to affined transformed coordinates? Shouldn't it be(self.kernel_size-1)//2-0.5
for making coordinate range between 0~h-1?The text was updated successfully, but these errors were encountered: