wlh
wlh
I have solved the first problem
I have solved the second problem. It is due to the version of cuda. I use cuda10.0, but pytorch0.4.1 uses cuda 9.0.
> > I have solved the second problem. > > It is due to the version of cuda. I use cuda10.0, but pytorch0.4.1 uses cuda 9.0. > > Hi, i...
'all.sh' is 'CUDA_VISIBLE_DEVICES=0,1 python3 tools/test_net.py --multi-gpu-testing --dataset fsod --cfg configs/fsod/voc_e2e_faster_rcnn_R-50-C4_1x_old_1.yaml --load_ckpt Outputs/fsod36000/ckpt/model_step71999.pth '
> What's your `all.sh`? The old `all.sh` has a small bug. CUDA_VISIBLE_DEVICES=0 python3 tools/train_net_step.py --save_dir SAVE_DIR --dataset fsod --cfg configs/fsod/voc_e2e_faster_rcnn_R-50-C4_1x_old_1.yaml --bs 1 --iter_size 1 --nw 1 --load_detectron data/pretrained_model/model_final.pkl CUDA_VISIBLE_DEVICES=0 python3...
> I updated the code, you can try the new code for your testing. I try new code and get the same result. o(╥﹏╥)o