I have run your training code following the instruction in README file, and I got a quick question.
I used the blurcozy2room scene.
"load_llff.py" seems like it reads all images from "images_1" folder (total 34 images) and also load "poses_bounds.npy" (29x17) file.
Then, in line 100~102, it checks whether the number of images and poses match or not (34 != 29).
Then it prints a message "Mismatch between imgs 34 and poses 29 !!!!" correctly, but it does not return because it is commented.
if poses.shape[-1] != len(imgfiles):
print( 'Mismatch between imgs {} and poses {} !!!!'.format(len(imgfiles), poses.shape[-1]) )
# return
Is it intentional?
I'll go through the code to check how the indices are handled anyway.
Hi, your work is very interesting!
I have run your training code following the instruction in README file, and I got a quick question. I used the blurcozy2room scene. "load_llff.py" seems like it reads all images from "images_1" folder (total 34 images) and also load "poses_bounds.npy" (29x17) file. Then, in line 100~102, it checks whether the number of images and poses match or not (34 != 29). Then it prints a message "Mismatch between imgs 34 and poses 29 !!!!" correctly, but it does not return because it is commented.
Is it intentional? I'll go through the code to check how the indices are handled anyway.