search

XuyangBai / PPF-FoldNet

PyTorch reimplementation for "PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors" https://arxiv.org/abs/1808.10322
99 stars 19 forks source link

Training leads to crash randomly #8

Closed WilliamKRobert closed 2 years ago

WilliamKRobert commented 4 years ago

When I run your code, my computer crashed and rebooted at line trainer.py/self.evaluate(0). I suspected it might relate to the conflict of some packages. Could you provide a complete list of your package versions? Such as PyTorch, tensorboardX, ect.? And your cuda and nvidia driver versions?

XuyangBai commented 4 years ago

Hi @WilliamKRobert

The package versions are shown in environment.yml and I use CUDA 9.0

WilliamKRobert commented 4 years ago

I created an environment exactly copying yours and used the same cuda version but the issue still exits. I am pretty sure it is raised when exec output=self.model(patches) in trainer.py/self.evaluate(0).

Anyone experienced the same issue?