Out of Memory for upscale factor 2 on images 256X256

alterzero / DBPN-Pytorch

The project is an official implement of our CVPR2018 paper "Deep Back-Projection Networks for Super-Resolution" (Winner of NTIRE2018 and PIRM2018)

https://alterzero.github.io/projects/DBPN.html

MIT License

565 stars 164 forks source link

Out of Memory for upscale factor 2 on images 256X256 #26

Closed NeuralBricolage closed 5 years ago

NeuralBricolage commented 5 years ago

I'm running on GTX 1080TI - i can upscale 2X images of 128X128 but results are quite bad - even colors are all off; but on 256X256 i'm running out of memory

python eval.py --upscale_factor=2 --model_type=DBPN --test_dataset=dset --model=models/DBPN_x2.pth

what are the GPU RAM expectations? if i add another 1080 will it solve the problem?

thank you

alterzero commented 5 years ago

Set flag --chop_forward to True for small memory GPU

NeuralBricolage commented 5 years ago

--chop_forward=True is the default - and i didn't help - i'm still getting OOM - and tbh i won't consider 1080TI to be a small memory GPU