Open
Description
I have encountered the following error. I have found a solution so I will share with you.
python run_nerf.py --config configs/fern.txt
Traceback (most recent call last):
File "run_nerf.py", line 878, in <module>
train()
File "run_nerf.py", line 542, in train
images, poses, bds, render_poses, i_test = load_llff_data(args.datadir, args.factor,
File "/nerf-pytorch/load_llff.py", line 246, in load_llff_data
poses, bds, imgs = _load_data(basedir, factor=factor) # factor=8 downsamples original imgs by 8x
File "/nerf-pytorch/load_llff.py", line 114, in _load_data
imgs = imgs = [imread(f)[...,:3]/255. for f in imgfiles]
File "/nerf-pytorch/load_llff.py", line 114, in <listcomp>
imgs = imgs = [imread(f)[...,:3]/255. for f in imgfiles]
File "/nerf-pytorch/load_llff.py", line 110, in imread
return imageio.imread(f, ignoregamma=True)
File "/usr/local/lib/python3.8/dist-packages/imageio/__init__.py", line 97, in imread
return imread_v2(uri, format=format, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/imageio/v2.py", line 360, in imread
result = file.read(index=0, **kwargs)
TypeError: read() got an unexpected keyword argument 'ignoregamma'
This issue is similar to Issue #190 in the original bmild/nerf repository, which is implemented based on Tensorflow (but not PyTorch).
Similar with this, to resolve it, update line 110 of load_llff.py as follows:
return imageio.imread(f, apply_gamma=True)I hope this helps!
Metadata
Assignees
Labels
No labels