xuanjihe / speech-emotion-recognition

speech emotion recognition using a convolutional recurrent networks based on IEMOCAP

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Request help

ShiJing123 opened this issue · comments

Hello, I have several problems when I am re-creating the code, I hope I can get help, thank you.

什么问题?

What is your problem?

您好,我在重现代码的时候报错,在定义X维度:X = tf.placeholder(tf.float32, shape=[None, 200, 40, 3])维度这里出错,修改之后,验证集的准确率在53%左右,而不是论文中的64%左右,我想问是因为在代码中没有加入attention机制的原因吗,我看attention那段代码注释掉了,谢谢回复。

64%是10交叉验证后的平均值,对于不同的验证集和测试集,你会发现效果相差很大,高的有70%多,差的50%几,而且你解决了样本不均衡问题吗?有问题可以给我写邮件xuanjihe@163.com,这样回复可能比较及时

好的,谢谢