deform_conv_pytorch
deform_conv_pytorch copied to clipboard
PyTorch Implementation of Deformable Convolution
Can it reach the paper benchmark?
hi, will you update the code to Visualize offsets?
Thanks for sharing the repo. I thought of the deform layer use as plug and play (right?) Replacing one of the `nn.Conv2d()` layers with `DeformConv2D()` produced this error: ``` result...
I wonder what is the reason of permuting the index of tensor p?
You did: N = offset.size(1) // 2, In that level the offset.size(1) is equal to 128 , and N suppuse to be the kernel size *2, means N=|R| And I...
Thanks for your sharing. I don't know why I change the input size like 56x56, It is can meet this question. I print the index.shape is torch.Size([8, 32, 28224]). Please...
thanks for your sharing, can you explain the meaning of q_lt, g_lt and x_q_lt ? thanks~
The `padding` in `DeformConv2D` doesn't work, because the shape of `x_offset` in function `_reshape_x_offset` is always `h*ks, w*ks`.