You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In this line, you backward gradient per image, so I guess it will consume more GPU resources when compute all gradients. I want to know how much GPU memory do you use in your practice. Thanks in advance!
The text was updated successfully, but these errors were encountered:
Yes we backward gradient per image, but I am not sure I understand why it consumes more GPU when computing all gradients? During training, we randomly sample 1024 pixels for each image so the GPU memory usage is only about 2-3GB if I remember correctly.
nerfmm/tasks/any_folder/train.py
Line 206 in 27faab6
In this line, you backward gradient per image, so I guess it will consume more GPU resources when compute all gradients. I want to know how much GPU memory do you use in your practice. Thanks in advance!
The text was updated successfully, but these errors were encountered: