search

jzbontar / mc-cnn

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
BSD 2-Clause "Simplified" License
706 stars 232 forks source link

questions about using kitti slow models! #10

Open kikyoyang opened 7 years ago

kikyoyang commented 7 years ago

hi, when running your code with kitti fast model, everything is ok. Nevertheless, I encounter the following problem when running the code using kitti slow models:

yang@yang-All-Series:~/mc-cnn$ ./main.lua kitti slow -a predict -net_fname net/net_kitti_slow_-a_train_all.t7 -left samples/pics/out_00_01.png -right samples/pics/out_00_00.png -disp_max 7
kitti slow -a predict -net_fname net/net_kitti_slow_-a_train_all.t7 -left samples/pics/out_00_01.png -right samples/pics/out_00_00.png -disp_max 7 
THCudaCheck FAIL file=/home/yang/torch/extra/cutorch/lib/THC/generic/THCStorage.c line=147 error=77 : an illegal memory access was encountered
luajit: cuda runtime error (77) : an illegal memory access was encountered at /home/yang/torch/extra/cutorch/lib/THC/generic/THCStorage.c:147

My GPU is TitanX, and I think it should have been running well. Hope for your reply.

kikyoyang commented 7 years ago

By the way, I use my own data for prediction, and the error occurs. If I use the KITTI dataset, the code still runs well. I am really confused about it, since the kitti fast model runs well using my own data. THX.