The document of torchvision.ops.deform_conv2d is not clear

📚 Documentation

From the documentation, I cannot get the exact meaning of 18(ie, 233) channels of the offset in a deformable convolution?

I want to visualize the offset of the deformable convolution with kernel size 3*3.
So It’s essential for me to know what’s the exact meaning of these channels.

I write down something possible here:

upper-left: ul
upper-right: ur
bottom-left: bl
bottom-right: br
up: u
bottom: b
right: r
left: l
center: c

possible offset layout (maybe not correct):
delta_ul_x, delta_ul_y,   delta_u_x, delta_u_y,     delta_ur_x, delta_ur_y;
delta_l_x, delta_l_y,       delta_c_x, delta_c_y,      delta_r_x, delta_r_y;
delta_bl_x, delta_bl_y,   delta_b_x, delta_b_y,     delta_br_x, delta_br_y;

Start with the torchvision.ops.deform_conv2d documentation and the issue's example of the 18 offset channels. Clarify the exact channel and spatial ordering for a 3×3 kernel, so users can map each pair to an offset when visualizing it; done means the documentation makes this mapping unambiguous.