MarvinTeichmann/KittiBox

terminate called after throwing an instance of 'std::bad_alloc' what(): std::bad_alloc Aborted (core dumped)

neuralearner opened this issue · 2 comments

neuralearner commented

Hi, great work so far! I've been experimenting with fastbox and have been able to get the demo to work. However, when I try to retrain my own model with the same Kitti dataset I'm getting the following error message when I run: python train.py

terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
Aborted (core dumped)

nghiattran commented

This sounds like you don't have enough memory to hold a batch. What is your batch_size value? How much memory do you have on GPU? Try to decrease your batch_size until tensorflow stop complaining about it.

  • 👍1
MarvinTeichmann commented

Closed due to inactivity. Should be fixable with a smaller batch size or bigger GPU memory. I recommend using 1080 TI for deep learning.