Unknown CUDA arch 8.0 or GPU not supported in DCNv2 setup about videoinr-continuous-space-time-super-resolution HOT 3 CLOSED

I think I solved this problem using a new version of DCNv2. I am using Python 3.8, and Torch 1.11 and CUDA 11.3on Ubuntu. Here's how to reproduce my setup.

Create a VINR conda environment.

conda create -n vinr python=3.8
conda activate vinr
pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113

Initialize and build the DCNv2 submodule.

git submodule add https://github.com/lucasjinreal/DCNv2_latest ./models/modules/
git submodule init
cd models/modules/DCNv2_latest
python3 setup.py build develop
cd ../..

Run demo

python demo.py --space_scale=4 --time_scale=8 --data_path="YOUR DATA"

from videoinr-continuous-space-time-super-resolution.

Yes. It seems CUDA arch 8.0 is too old. Maybe try a newer version of it.

from videoinr-continuous-space-time-super-resolution.

我运行时遇到的两个问题解决方案：
https://blog.csdn.net/qq_37346140/article/details/127684795
CharlesShang/DCNv2#14

from videoinr-continuous-space-time-super-resolution.