Griovwe

I have the same problem, do you fix it?

I modify the make.sh file, make -D_GLIBCXX_USE_CXX11_ABI=0, Here is my make.sh file: #!/usr/bin/env bash TF_INC=$(python -c 'import tensorflow as tf; print(tf.sysconfig.get_include())') echo $TF_INC CUDA_PATH=/usr/local/cuda/ cd roi_pooling_layer nvcc -std=c++11 -c -o...