배현웅 HyunWoong Bae
배현웅 HyunWoong Bae
Another possible cause in the segmentation is the **pixel value**. **The pixel value for the labeling should be within 20 (the largest index for the label)** I misunderstand that the...
thank you! It resolves same error when shifting the pipeline to gpu using .to('cuda')
No i'm working machine having 128GB DRAM and 24GB VRAM i tried on another environment (pytorch 2.2.0 of py3.9.18, cuda 11.8 and cudnn8.7.0). It works! Thank you for helping
@JGyoung-UCAS Actually, i'm not working with this code right now.. However, sharing my thoughts with you, I think the implementation of the "self.head" should be concerning with "task_id", not "args.scale"...
It seems that this is mentioned in the following comment: https://github.com/kssteven418/BigLittleDecoder/issues/6#issuecomment-2127891521, specifically in reference to the command `python -m pip install -e .`