HughCai

A problem about one game in ALE cannot be trained

1

Hi, Kai! I find an issue which happens when I set the game "defender" as the environment. It only displays hyper-parameter setting "args", and however, any training results aren't output,...

Effect of the input size on the performance of SimVP

2

Hi, Gao I find the input size is almost smaller than 128 in the paper. So, I take a training on my own dataset which are same expect for different...

Hi, Whether are there any key points or tricks when re-implement the model? I tried to implement it without `torch_geometric`, but have some problems: 1. the training loss reduces slowly...