Object Detection inference is not working

kexinyi / ns-vqa

Neural-symbolic visual question answering

262 stars 62 forks source link

Object Detection inference is not working #5

Open ggaemo opened 5 years ago

ggaemo commented 5 years ago

python tools/test_net.py \ --dataset clevr_original_val \ --cfg configs/baselines/e2e_mask_rcnn_R-50-FPN_1x.yaml \ --load_ckpt ../../data/pretrained/object_detector.pt \ --output_dir ../../data/mask_rcnn/results/clevr_val_pretrained

When I run the script above, it gives out a cudaCheckError

cudaCheckError() failed : no kernel image is available for execution on the device .

it happens with the RoIAlignFunction

sjtuytc commented 5 years ago

you need to have a GPU card with cuda

ggaemo commented 5 years ago

I already have Titan X with CUDA installed. It works well with other codes with pytorch

sjtuytc commented 5 years ago

I do not have a problem with 1080Ti, you can check repo of maskrcnn to get help.