search

VITA-Group / FasterSeg

[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang
MIT License
524 stars 107 forks source link

CUDA out of memory: GeForce GTX 1650. #56

Closed TamuseDomain closed 3 years ago

TamuseDomain commented 3 years ago

Hi! Thank you Wuyang, Xinyu, Xianming, Qian, Yuan and Zhangyang, for sharing your great work.

I'm trying your project, but at <>, I get the following error:

image

I'm running on: Ubuntu 18.04.5 LTS Dell G3 3590 Core Intel i5-9300H 8 GB RAM NVIDIA GeForce GTX 1650 (4GB graphic memory)

I already tried turning down the batch size, crop size and even the number of workers. Could the GeForce be able to run this work, or do I need a more capable GPU (>= 11G graphic memory)?

Thank you again!

chenwydj commented 3 years ago

Hi @TamuseDomain!

Thank you for your interest in our work!

We did not try our code on GTX 1650. I think capable GPU memory is required.