Closed rakshith95 closed 2 years ago
This seemed to be an issue with loading the intrinsics npy file, with loadtxt
failing sometimes. I added a try except with try: np.loadtxt() except: np.load()
in datasets.py
, and it appears to have fixed the problem.
numpy version 1.21.5
Hello, While running the training script train_kbnet_void1500.sh, I inevitably end up getting this error after 5000+ steps:
Have you encountered this error before, and do you have an idea of why it could be occurring? I guess it must be something to do with my data, but I have no idea what. I'm running torch 1.3.0, and torchvision 0.4.1