zx66zx的博客

看代码提示里写的 ‘min’是判断 schedular.step(val_loss) 里输入的val_loss是否减小来更改lr的值的我是这样写的：scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=0.5, patience=2, verbose=True, threshold=0.0001, threshold_mode='rel', cooldown=0, min_..