deformable-convolution-pytorch

deformable-convolution-pytorch copied to clipboard

Extend this to 1-D

8

I'm trying to extend `ConvOffset2d` to 1d convolution as well. While this can be easily done by simply consider a length-L 1D tensor as a dimension [1xL] 2D tensor, the...

shaojieb

hello,is it useful to use dcn on 1x1conv?

kirkzZ

run nvcc -c -o deform_conv_cuda_kernel.cu.o deform_conv_cuda_kernel.cu -x cu -Xcompiler -fPIC -std=c++11 happens error，nvcc fatal : Cannot find compiler 'cl.exe' in PATH

b762927

Hi, @1zb, Thanks for your great work! Can you add a license to this repository such that this code can be used in our own projects?

aaronpetok

Is it possible to support 3D convolution?

8

I want to use 3D version of deformable convolution, but it seems like your code only support 2D. What change should be made to adapt to 3D convolution? Is it...

leao1995

offset number?

1

why offset numbers are kW x kH x 2? In the paper ,offset= 2 x N, the N is number of channel。

zhuwanling

Not working on pytorch 0.4.1

3

It is not working on pytorch 0.4.1.

crewleader

I ran the sh make.sh and then CC=g++ python build.py. It seems that It is building fine, however after running the test.py I have got error. Please note that in...

Simpatech-app

leon532

梯度测试不通过

21

- 我使用 [gradcheck](https://github.com/pytorch/pytorch/blob/master/torch/autograd/gradcheck.py) 提供的梯度测试方法，测试梯度不通过。比较数值梯度和解析梯度，其每一个非零数（非边界位置）的符号，位置等都是一样的，但就是数值差了一点。 - 另外，在cifar10上简单测试，没有效果，它在使用上有什么要注意的吗，可不可以交流一下。

lshiwjx