RuntimeError: CUDA error: out of memory

[guangzhao17]

run:
python main.py --dataset my_dataset --light True
error:
RuntimeError: CUDA error: out of memory

I had sucessfully installed pytorch with GPU on computer.

---

import torch
torch.cuda.is_available()
True

---

This works well,and I find no error when running other pytorch codes.

[znxlwm]

Above error means, your GPU memory is insufficient for training.

We trained model without light flag using V100 32GB, with light flag using 1080Ti 11GB.

Thank you

[w32zhong]

Same error here, I solved it by setting a lower base channel number than the default one (via --ch).