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:
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;
Could you add a bit more background to the question, please?
Is “deformable convolution” a custom modules, which uses these parameters?
It is a newly added module in torchvision, however, the document about the offset is not clear.
Thanks for the reference! Could you point me to the
2*3*3 usage from your original post?