search

JXingZhao / EGNet

EGNet:Edge Guidance Network for Salient Object Detection (ICCV 2019)
311 stars 62 forks source link

How to avoid CUDA out of memory #28

Open Goru1890 opened 3 years ago

Goru1890 commented 3 years ago

I'm trying to test my own dataset and I'm getting back a CUDA out of memory message:

RuntimeError: CUDA out of memory. Tried to allocate 1.19 GiB (GPU 0; 10.76 GiB total capacity; 6.91 GiB already allocated; 851.81 MiB free; 1.51 GiB cached)

Could it be because of my pytorch version? pytorch version ==1.3.1

user-wu commented 3 years ago

I'm trying to test my own dataset and I'm getting back a CUDA out of memory message:

RuntimeError: CUDA out of memory. Tried to allocate 1.19 GiB (GPU 0; 10.76 GiB total capacity; 6.91 GiB already allocated; 851.81 MiB free; 1.51 GiB cached)

Could it be because of my pytorch version? pytorch version ==1.3.1

maybe you need a RTX 3090