Loading training data : Killed

[rohitdhote111]

I am training model on custom dataset. I have created 3 files (transforms_train/test/val.json) and 2 folders(colmap_text/sparse) using scripts/colmap2nerf.py and stored the images in separate folder.

**Note: The files generated using colmap2nerf.py was on windows machine and testing nerf2mesh algo on linux machine as colmap was giving error on linux.**

but I am getting message as Killed with no error at around 75% of data uploading in both trials (colmap and nerf data format). I don't have any memory shortage. Please let me know what I am missing?

Trial 1 root@1dcb588ae75a:/home/data2/nerf2mesh# python main.py data/custom/ --workspace trial_custom -O --data_format colmap --bound 16 --enable_cam_center --enable_cam_near_far --scale 0.3 --stage 0 --lambda_entropy 1e-3 --clean_min_f 16 --clean_min_d 10 --lambda_tv 2e-8 --visibility_mask_dilation 50 [INFO] ColmapDataset: image H = 4000, W = 6000 [INFO] 570 image exists in all 570 colmap entries. [INFO] ColmapDataset: load poses (570, 4, 4), points (311022, 3) [INFO] extracting sparse depth info... 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 570/570 [00:00<00:00, 1511.86it/s] [INFO] extracted 4704.99 valid sparse depth on average per image Loading train data: 74%|████████████████████████████████████████████████████████████████▍ | 369/498 [02:11<01:32, 1.39it/s]Killed

Trial 2: root@1dcb588ae75a:/home/data2/nerf2mesh# python main.py data/custom/ --workspace trial_custom -O --data_format nerf --bound 16 --enable_cam_center --enable_cam_near_far --scale 0.3 --stage 0 --lambda_entropy 1e-3 --clean_min_f 16 --clean_min_d 10 --lambda_tv 2e-8 --visibility_mask_dilation 50 Loading train data: 75%|█████████████████████████████████████████████████████████████████▏ | 373/498 [02:16<02:02, 1.02it/s]Killed

[rohitdhote111]

It was ram issue. problem solved!