run nice-slam for open dataset, IndexError: list index out of range

[parastoobakhtiarii]

Hi, I hope you are doing well. thank you for the great documentation. I am trying to run nice-slam on Terrasentia dataset, I'm using python 3.9 and

python -c "import torch; print(torch.__version__); print(torch.version.cuda); print(torch.cuda.is_available())"
2.5.1+cu121
12.1
True

I get this error: 2025-03-19 15:19:34,054 - INFO - Running NICE-SLAM with config: configs/Terrasentia/terrasentia.yaml 2025-03-19 15:19:34,054 - INFO - Output directory: /media/asaas/DATA/Parastou/nice-slam/output/Terrasentia 2025-03-19 15:19:34,054 - INFO - Using NICE-SLAM: True INFO: The output folder is /media/asaas/DATA/Parastou/nice-slam/output/Terrasentia INFO: The GT, generated and residual depth/color images can be found under /media/asaas/DATA/Parastou/nice-slam/output/Terrasentia/tracking_vis/ and /media/asaas/DATA/Parastou/nice-slam/output/Terrasentia/mapping_vis/ INFO: The mesh can be found under /media/asaas/DATA/Parastou/nice-slam/output/Terrasentia/mesh/ INFO: The checkpoint can be found under /media/asaas/DATA/Parastou/nice-slam/output/Terrasentia/ckpt/ 2025-03-19 15:19:34,479 - INFO - NICE-SLAM initialized successfully. Process Process-2: Traceback (most recent call last): File "/home/asaas/anaconda3/envs/nice-slam/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/asaas/anaconda3/envs/nice-slam/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/media/asaas/DATA/Parastou/nice-slam/src/NICE_SLAM.py", line 276, in mapping self.mapper.run() File "/media/asaas/DATA/Parastou/nice-slam/src/Mapper.py", line 544, in run idx, gt_color, gt_depth, gt_c2w = self.frame_reader[0] File "/media/asaas/DATA/Parastou/nice-slam/src/utils/datasets.py", line 78, in getitem color_path = self.color_paths[index] IndexError: list index out of range

Would you please tell me what can be the potential issue?

my dataset contains 3998 rgb images and 3998 depth images. the attached image. and this is the yaml file:

inherit_from: configs/Own/own.yaml

cam:
  H: 480  # Image height
  W: 640  # Image width
  fx: 342.40289471  # Focal length in x (from left camera intrinsics)
  fy: 342.20510857  # Focal length in y (from left camera intrinsics)
  cx: 408.75398427  # Principal point x (from left camera intrinsics)
  cy: 220.34050007  # Principal point y (from left camera intrinsics)
  png_depth_scale: 1000.0  # For depth image in png format
  crop_edge: 0

mapping:
  bound: [[-10, 10], [-5, 5], [-1, 3]]  # Adjust based on field size and camera range
  marching_cubes_bound: [[-10, 10], [-5, 5], [-1, 3]]  # Same as bound for consistency

data:
  input_folder: /media/asaas/DATA/Parastou/nice-slam/Datasets/Terrasentia
  output: /media/asaas/DATA/Parastou/nice-slam/output/Terrasentia

model:
  use_color: True
  use_depth: True
  voxel_size: 0.05
  truncation: 0.1

optimization:
  num_iterations: 1000
  learning_rate: 0.001

output:
  save_mesh: True
  save_trajectory: True

Thanks.