search

MILVLG / bottom-up-attention.pytorch

A PyTorch reimplementation of bottom-up-attention models
Apache License 2.0
292 stars 75 forks source link

Stuck when extracting features #106

Open dongfengxijian opened 1 year ago

dongfengxijian commented 1 year ago

When I use the extract_features.py to extract features, the process seem be stuck. I tired the two commands：

python3 extract_features.py --mode caffe \ --num-cpus 2 --gpus '0,1,2,3' \ --extract-mode roi_feats \ --min-max-boxes '20, 20' \ --config-file configs/caffe/test-caffe-r101.yaml \ --image-dir './datasets/demo/' --bbox-dir './output/features/' --out-dir './output/bbox/' --fastmode

python3 extract_features.py --mode caffe \ --num-cpus 0 --gpus '0,1,2,3' \ --extract-mode roi_feats \ --min-max-boxes '10, 100' \ --config-file configs/caffe/test-caffe-r101.yaml \ --image-dir './datasets/demo/' --bbox-dir './output/features/' --out-dir './output/bbox/'

However, when I removed the --fastmode, it was still stuck. Addition, I can find the process through top command but I can't find it through nvidia-smi command. 微信截图_20230526224537

ther-0319 commented 10 months ago

Have you solved this problem? Can you tell me how to solve it?

1MurasaKi commented 9 months ago

I have also encountered this problem. Can you tell me how to solve it