kris-yangjs

conflict between pytorch and cupy

3

Thanks for your amazing work. I tried the environment installation according to your readme.md. But I found a question: pythorch 1.1.0 is based on cudnn7.5.1, but cupy6.0 is based on...

Problem when training with one GPU

5

I change some of the code and the script "train_PBAFN_stage1.sh". And my environment: RTX2080Ti pytorch = 1.1.0 cudatoolkit = 9.0 cupy = 6.0.0 Just the GPU differ from your's and...

PLE Loss 没有优化

1

多任务模型的 ple 中是否没有按照原文实现 Joint Loss Optimization for MTL？

Dataset download fail

1

Hello, Thank you for your great work I tried to download the dataset, but I couldn't connect to the link of dataset MPV

"RuntimeError: CUDA error: out of memory" when train TOM with RTX2080Ti

2

Hello, thank you for your amazing work! I tried to train the model, and I finished the GMM step. But when I tried to train the TOM with one GPU(2080Ti),...