SHI-Labs / OneFormer

OneFormer: One Transformer to Rule Universal Image Segmentation, arxiv 2022 / CVPR 2023
https://praeclarumjj3.github.io/oneformer
MIT License
1.41k stars 128 forks source link

Cuda Out Of Memory #50

Closed christophTUM closed 1 year ago

christophTUM commented 1 year ago

When doing inference on my own data i get this warning: Attempting to copy inputs of <function sem_seg_postprocess at 0x7fc057578a70> to CPU due to CUDA OOM

Does this in the end affect the performance and is there a way to fix this?

I am using one RTX 2070 for inference.