weights = np.repeat(depth_gts[i]['error'][:,None,None], 3, axis=2) # N x 1 x 3 KeyError: 'error'

[rockywind]

Hi, When I run my own data in colmap style, I met the erroe below.

weights = np.repeat(depth_gts[i]['error'][:,None,None], 3, axis=2) # N x 1 x 3
KeyError: 'error'

My config is that below.

expname = parking2
basedir = ./logs/parking2
datadir = /rockywin.wang/NeRF/DSNeRF/data/parking2
dataset_type = llff #colmap_llff
factor = 4 
llffhold = 8
N_rand = 4096
N_samples = 64
N_importance = 128
use_viewdirs = True
raw_noise_std = 1e0
no_ndc = True
colmap_depth = True
depth_loss = True
depth_lambda = 0.1
i_testset = 5000
i_video = 10000
N_iters = 50000

[dunbar12138]

Hi, thanks for pointing it out.

It's because of the inconsistent label fields in loading depths. I have updated the function. Can you try the latest version?

[rockywind]

Thank you very much! It's work!