4uiiurz1 / pytorch-deform-conv-v2

PyTorch implementation of Deformable ConvNets v2 (Modulated Deformable Convolution)
MIT License
743 stars 141 forks source link

a problem of _get_p_0 #16

Open FourierTransform opened 4 years ago

FourierTransform commented 4 years ago

Firstly,thanks for your work I noticed that p_0_x and p_0_y all start from 1,so the first coordinate is (1,1).But if the kernel_size isn't 1,there will be negative coordinate.Thought you use torch.clamp to aviod those negative value.But I don't think it is the convolution operation described by the author.I think the coordinate should begin from ((kernel_size-1)/2,(kernel_size-1)/2)