Segmentation fault(core dumped)

[Millielele]

when I run CUDA_VISIBLE_DEVICES=1 python generate_tsv.py --net res101 --dataset vg --out test.tsv --cuda
It said:

  load checkpoint load_dir/faster_rcnn_res101_vg.pth
  load model successfully!
  load model load_dir/faster_rcnn_res101_vg.pth
  Segmentation fault (core dumped)

why this happen? How to solve that?

CUDA10.0
python3.6
pytorch1.0
gcc 5.4

[Alchemistyui]

same problem... did you solve it?

[manmolecular]

Same here, is there any solution?

EDIT: Solved by using the exact following packages (python3.6, conda)

conda install pytorch==1.0.1 torchvision==0.2.2 cudatoolkit=10.0 -c pytorch

versions from conda list:

cudatoolkit               10.0.130                      0
pytorch                   1.0.1           py3.6_cuda10.0.130_cudnn7.4.2_2    pytorch
torchvision               0.2.2                      py_3    pytorch