search

kwea123 / ngp_pl

Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)
MIT License
1.26k stars 156 forks source link

Process death when using mip-nerf 360 data #102

Closed minsoo5403 closed 1 year ago

minsoo5403 commented 1 year ago

he process displays a Killed message when executed with the following command:

python train.py --root_dir data/360_v2/garden --exp_name garden --dataset_name colmap

GridEncoding: Nmin=16 b=1.31951 F=2 T=2^19 L=16 Using 16bit native Automatic Mixed Precision (AMP) GPU available: True (cuda), used: True TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available: False, using: 0 HPUs Missing logger folder: logs/colmap/garden Loading 161 train images ... 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████| 161/161 [00:37<00:00, 4.34it/s] Killed

Use the - ubuntu 22.04 / cuda 11.3

Is there a way to solve the problem?

minsoo5403 commented 1 year ago

Runs when I add a scale. --scale 16.0