Label indices do not match class weights or paper notation

[florianblume]

Hi,

first of all thanks for your great work and providing this dataset!

Unfortunately I just realized that the labeling indices that you provide in the annotation files, i.e. {'neutral': 0, 'surprise': 1, 'fear': 2, 'sadness': 3, 'joy': 4, 'disgust': 5, 'anger': 6}, do not match how you specify them in the paper and - more importantly - the order of the weights in the README.md: [4.0, 15.0, 15.0, 3.0, 1.0, 6.0, 3.0]. Given the occurrence counts, I'm assuming that the weight 1.0 belongs to neutral, which is index 0 in the annotation files but index 4 in the weights.

Could you correct the weights so that users won't accidentally use the wrong assignments if they don't compute the weights themselves (like me)?

The correct weights are [1.0, 3.0, 15.0, 6.0, 3.0, 15.0, 4.0].

Best,
Florian

[Triaill]

Hi, 你好，

first of all thanks for your great work and providing this dataset!首先感谢您的出色工作并提供此数据集！

Unfortunately I just realized that the labeling indices that you provide in the annotation files, i.e. {'neutral': 0, 'surprise': 1, 'fear': 2, 'sadness': 3, 'joy': 4, 'disgust': 5, 'anger': 6}, do not match how you specify them in the paper and - more importantly - the order of the weights in the README.md: [4.0, 15.0, 15.0, 3.0, 1.0, 6.0, 3.0]. Given the occurrence counts, I'm assuming that the weight 1.0 belongs to neutral, which is index 0 in the annotation files but index 4 in the weights.不幸的是，我刚刚意识到您在注释文件中提供的标签索引，即 {'neutral': 0, 'surprise': 1, 'fear': 2, 'sadness': 3, 'joy': 4, 'disgust': 5, 'anger': 6} ，与您在论文中指定的方式不匹配 - 更重要的是 - README.md 中权重的顺序： [4.0, 15.0, 15.0, 3.0, 1.0, 6.0, 3.0] 。考虑到出现次数，我假设权重1.0属于中性，即注释文件中的索引0但权重中的索引4 。

Could you correct the weights so that users won't accidentally use the wrong assignments if they don't compute the weights themselves (like me)?您能否更正权重，以便用户在不自己计算权重（像我一样）的情况下不会意外地使用错误的分配？

The correct weights are [1.0, 3.0, 15.0, 6.0, 3.0, 15.0, 4.0].正确的权重是 [1.0, 3.0, 15.0, 6.0, 3.0, 15.0, 4.0] 。

Best, 最好的， Florian 弗洛里安

Same for me!May I ask if you've solved it?

[florianblume]

Hey,

I solved it by just using the corrected weights that I posted. I opened this issue so that other people would not take the wrong weights from here.

So just use the corrected weights!

[Triaill]

Hey,

I solved it by just using the corrected weights that I posted. I opened this issue so that other people would not take the wrong weights from here.

So just use the corrected weights!

Thank you very much for your guidance!I‘m not sure about how to set class weights,could you give me some advice？
Which files and code should I modify?