You should compile all the. sh files which are in other folders, such as grouping folder . ------------------ 原始邮件 ------------------ 发件人: "DRosemei"<[email protected]> 发送时间: 2020年1月8日(星期三) 下午5:41 收件人: "Yang7879/3D-BoNet"<[email protected]>; 抄送: "fxy2012"<[email protected]>;"Mention"<[email protected]>; 主题: Re: [Yang7879/3D-BoNet]tensorflow.python.framework.errors_impl.NotFoundError: (#17) Have you solved this problem? I modified "tf_sampling_compile.sh" like below but I still get this problem. I use python 2.7 and tf1.2 `#/bin/bash /usr/local/cuda-8.0/bin/nvcc tf_sampling_g.cu -o tf_sampling_g.cu.o -c -O2 -DGOOGLE_CUDA=1 -x cu -Xcompiler -fPIC py27 + TF1.2 g++ -std=c++11 tf_sampling.cpp tf_sampling_g.cu.o -o tf_sampling_so.so -shared -fPIC -I /home/rose/anaconda3/envs/3DBoNet/lib/python2.7/site-packages/tensorflow/include -I /usr/local/cuda-8.0/include -lcudart -L /usr/local/cuda-8.0/lib64/ -O2 -D_GLIBCXX_USE_CXX11_ABI=0` &mdash; You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.