difference between DCNv2 and deform_conv2d in torchvision

[sparshgarg23]

Since both torchvision's deform_conv2d and this repo tend to replicate the deformable convolutional net,would like to know what seperates this implementation from the torch implementation.

[DonggeunYu]

What's the difference?

[ibayer]

@Licht-T

Thanks for contributing https://github.com/pytorch/vision/pull/2791 to torchvision! We are wondering if we could use your torchvision implementation as drop in replacement for the cuda extension in DCNv2.

I think this would require replacing

• https://github.com/CharlesShang/DCNv2/blob/c7f778f28b84c66d3af2bf16f19148a07051dac1/dcn_v2.py#L25
• https://github.com/CharlesShang/DCNv2/blob/c7f778f28b84c66d3af2bf16f19148a07051dac1/dcn_v2.py#L40
• https://github.com/CharlesShang/DCNv2/blob/c7f778f28b84c66d3af2bf16f19148a07051dac1/dcn_v2.py#L153
• https://github.com/CharlesShang/DCNv2/blob/c7f778f28b84c66d3af2bf16f19148a07051dac1/dcn_v2.py#L166

with their torchvision equivalents.

The same question has bee raised elsewhere as well https://github.com/jinfagang/DCNv2_latest/issues/29.

Would be great to get you thoughts on using your torchvision implementation here. This might eliminate the need to compile the cuda extension and therefore simply integration of DCNv2 a lot.

Implementation in torchvision

• https://pytorch.org/vision/stable/generated/torchvision.ops.deform_conv2d.html#torchvision.ops.deform_conv2d
• https://pytorch.org/vision/main/generated/torchvision.ops.ps_roi_pool.html?highlight=ps_roi#torchvision.ops.ps_roi_pool
• ? https://pytorch.org/vision/main/generated/torchvision.ops.ps_roi_align.html

edit: add links to torchvision docs

[ibayer]

Not yet tested but the README sounds promising:

PyTorch Deformable Convolutional Networks v2 (no compile required) This is developed for use with FairMOT inference. Referenced PyTorch-Deformable-Convolution-v2 for the use of torchvision.ops.deform_conv2d. Referenced DCNv2 for the class constructor signature.

https://github.com/liyier90/pytorch-dcnv2