About the score range

[geknow]

Hello, in some cases, I found some indicators are negative. Are they normal?

[geknow]

这个指标是越高越好，还是越低越好？或者说，多个model，在相同的数据集上进行imageReward的评测，是不是得分越高越好？

[xujz18]

When you test with ImageReward, the higher ImageReward, the better.
The reward is normalized to have a mean of 0 and a standard deviation of 1. When testing stable diffusion v1.4 on our metric set, the scope of the reward is observed to have 62.4% of [-1,1] and 98.2% of [-2,2].
You can refer to: Issue 5, Issue 7, Issue 22, and Issue 40.
指标是越高越好的；多个model在相同数据集使用ImageReward评测，越高越好。