gandad

mix up strategy decreased the trainning samples by 50%

1

Hello yu4u, It seems that the mixup strategy decreases the trainning smaple number by 50%. Have you tested the result of keeping the sample number? e.g., for each min-batch,we create...

我的模型为什么只说不做啊

2

工程文件是用cursor在win11下创建的。测试了好多指令，都是只说不做。  模型配置如下：