←Backanonymous0522/RAANFork0Copy as MarkdownView on GitHub↗32 stars·3 forks·Python·MIT·0 viewsRAAN The CUDA and Pytorch version that is used for this work: ~~~ 'CUDA==10.0', 'torch==1.1.0', 'CUDNN==7.5.0' ~~~ Warning: We tried CUDA11.0+Torch1.7.1 on RTX3090, the AP performance is significantly lower than the aforementioned environment setup. Features