list index out of range

[Zvyozdo4ka]

why is it always list index out of range, how many images am I supposed to employ? Once it was mentioned about 200 images, but i can't run 152 images. What is the maximum?

    calib_line=lines[idx]
IndexError: list index out of range

[Zvyozdo4ka]

it got till this line after removing 62 images:

scene centroid [-0.10412887 -0.48836884  3.7554102 ]
scene scale 1.8039371967315674
Using default sphere of radius 0.5
phase.iter_nr 1000 loss  0.2094968855381012
phase.iter_nr 2000 loss  0.10482532531023026
phase.iter_nr 3000 loss  0.08739101886749268
phase.iter_nr 4000 loss  0.04008416086435318
/usr/local/lib/python3.8/dist-packages/torch/optim/lr_scheduler.py:139: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimizer.step()` before `lr_scheduler.step()`.  Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
  warnings.warn("Detected call of `lr_scheduler.step()` before `optimizer.step()`. "

[RaduAlexandru]

Hi @Zvyozdo4ka,

I'm not sure what causes the list index out of range in your case. I mention the 200 images because that seems to give the best results but you can probably use more if you have more GPU memory. Also in some experiments I could use almost 20 cameras and still get good results but this is heavily dependent on camera configuration and the scene.

As for the warning regarding the learning rate scheduler, it shouldn't affect final results but it's an issue I should fix so thank you for pointing it out!

[Zvyozdo4ka]

@RaduAlexandru Thank you so much!