Closed rockywind closed 3 years ago
Hello!
I inherited these scripts from OpenPCDet, so unfortunately I'm not an expert at them. I would recommend not to use the bash scripts, and just run the python scripts directly via:
python -m torch.distributed.launch --nproc_per_node=2 train.py --launcher pytorch --batch_size 4 --cfg_file /newnfs/zzwu/08_3d_code/CaDDN-master/tools/cfgs/kitti_models/CaDDN.yaml
Closing due to inactivity
I apologize for the delay. It can run in the format of this.CUDA_VISIBLE_DEVICE=0,3 python train.py --batch_size 4 --cfg_file /newnfs/zzwu/08_3d_code/CaDDN/tools/cfgs/kitti_models/CaDDN.yaml
Thank you for your help in advance. When I run the scipts
bash scripts/dist_train.sh 2 --batch_size 4 --cfg_file /newnfs/zzwu/08_3d_code/CaDDN-master/tools/cfgs/kitti_models/CaDDN.yaml
The program was stuck here. `(CaDDN05) zizhang.wu@shaxbw06:/newnfs/zzwu/08_3d_code/CaDDN-master/tools$ sh train.shSetting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
`