John1231983

I think the problem is shape order. It needs order as NxCxHxW, instead of NxHxWxC in tensorflow. After obtained the result of deformable convolution using NxCxHxW, I need to reorder...

Thanks for your help. I checked the code that confirmed only support NCHW format. Sorry, I did not read it before. For the second question, do you think is it...

I guess this is learning rate multiplier for bias and weight.

Thanks to your great direction. I have completed it and it worked well. However, I have one question for offset. In traditional implementation, the offset did not include rate/dilated parameter...

I think it is necessary. I guess the author is missing because each element of convolution will correspond to offset element. On other hands, the offset element controls the direction...

Thanks. The problem is that related to cuda.h. I checked in the tensorflow and noone can solve it in tensorflow 1.4. They only suggest downgrading to 1.2.1 ``` /usr/local/lib/python3.5/dist-packages/tensorflow/include nvcc...

Ok. Now I have succeeded to build in tensorflow 1.4 that install from pip3. This is my script, you can use it to update the README nvcc file ``` TF_INC=$(python3...

Hello all, I am using g++ 4.9 and cuda 8.0, cudnn 6.0. I installed tensorflow from `pip3 install tensorflow-gpu==1.3`. When I run `./nvcc_compile.sh`. I got the error ``` nvcc warning...

Hi. Thanks for your reply. What tf version did you use?

Hi @Zardinality: Your method worked fine in personal computer by copy ``` if [ ! -f $TF_INC/tensorflow/stream_executor/cuda/cuda_config.h ]; then cp ./cuda_config.h $TF_INC/tensorflow/stream_executor/cuda/ fi ``` However, for the server, I cannot...