How to test?

[wlh0517]

When I run 'all.sh' to test, there is a question. ''' support annotation number: 14862 INFO test_engine.py: 536: loading checkpoint Outputs/SAVE_DIR/ckpt/model_step479999.pth Killed ''' The code is killed.

[fanq15]

What's your all.sh? The old all.sh has a small bug.

[wlh0517]

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 tools/test_net.py --dataset fsod --cfg configs/fsod/voc_e2e_faster_rcnn_R-50-C4_1x_old_1.yaml --load_ckpt Outputs/SAVE_DIR/ckpt/model_step479999.pth

Because I only have one GPU, so I set the default of '--multi-gpu-testing' to False in 'test_net.py'. As the picture showing, load and then killed. When the code running, I use 'nvidia-smi' and find that it only uses 573MB memory of GPU. When the code running, I use 'top' and find memory is OK.

[fanq15]

I updated the code, you can try the new code for your testing.

[wlh0517]

I updated the code, you can try the new code for your testing.

I try new code and get the same result. o(╥﹏╥)o

[fhong-jpg]

@wlh156423 Could you share me your trained model? Thanks.

[gmkproofing]

I updated the code, you can try the new code for your testing.

I try new code and get the same result. o(╥﹏╥)o

Hi，I have met the same problem with you , did you solve it ? Thank you very much.