对evaluate_benchmark.py中分数列表初始化存在疑问

[ShangZhang0407]

evaluate_benchmark.py中的第111line~第113line，按照数据格式，if c["name"] not in criteria总是为false，修改为if c["name"] not in data["scores"]: 是不是更符合逻辑一点

[hljjjmssyh]

@A-Quarter-Mile Hi Wu,

I noticed a few issues in the calculate_scores.py script, including a missing import for the argparse package and some incorrect variable names. Could you please verify that the code logic aligns with what's described in the paper and fix these errors?

Thanks!

[ShangZhang0407]

@A-Quarter-Mile Hi Wu,

I noticed a few issues in the calculate_scores.py script, including a missing import for the argparse package and some incorrect variable names. Could you please verify that the code logic aligns with what's described in the paper and fix these errors?

Thanks!

yes, I also found these errors, we need to modify this calculate_scores.py code when using it.

[A-Quarter-Mile]

@ShangZhang0407 @hljjjmssyh Thanks for pointing out. Fixed now.