search

Jeff-sjtu / HybrIK

Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021
MIT License
1.16k stars 142 forks source link

I encountered some error #191

Open JSWLDG opened 10 months ago

JSWLDG commented 10 months ago

I want to train hybrik model so I comman

./scripts/train_smpl_cam.sh test_3dpw configs/256x192_adam_lr1e-3-res34_smpl_3d_cam_2x_mix_w_pw3d.yaml

then

Traceback (most recent call last): File "./scripts/train_smpl_cam.py", line 361, in main() File "./scripts/train_smpl_cam.py", line 208, in main mp.spawn(main_worker, nprocs=ngpus_per_node, args=(opt, cfg)) File "/home/jsw/anaconda3/envs/bybrik/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 240, in spawn return start_processes(fn, args, nprocs, join, daemon, start_method='spawn') File "/home/jsw/anaconda3/envs/bybrik/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 198, in start_processes while not context.join(): File "/home/jsw/anaconda3/envs/bybrik/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 140, in join raise ProcessExitedException( torch.multiprocessing.spawn.ProcessExitedException: process 0 terminated with signal SIGSEGV

this error messege was emerged.

I want to know what's the problem

And I use only one gpu. Is that a reason why that messege occured??

biansy000 commented 10 months ago

It may be the reason. You may try changing https://github.com/Jeff-sjtu/HybrIK/blob/9b8681dcf3c902dd5dacc01520ba04982990e1e2/configs/256x192_adam_lr1e-3-res34_smpl_3d_cam_2x_mix_w_pw3d.yaml#L66 to WORLD_SIZE: 1