ZhuoYulang
commented
9 months ago I apologize for not responding to your email in a timely manner The answer of the first question: the second dimension is sequence size. The shape of every raw features are [batch_size, sequence_size, embedding_size]. The answer of the second question: in our input data, a batch represent a batch of utterances. We don't consider the conversations here. By the way, I am from Inner Mongolia University, China. Could you tell me what school you're from? I'd like to make friends with you, which will help us further discuss some work or ideas on multimodality
------------------ 原始邮件 ------------------ 发件人: "ZhuoYulang/IF-MMIN" @.>; 发送时间: 2023年12月12日(星期二) 晚上8:03 @.>; @.***>; 主题: [ZhuoYulang/IF-MMIN] Questions about input data (Issue #3)
Hello, I have some questions about the input data. First, I see that when the original features you provided are loaded, all the three modal features have three dimensions, the first dimension is batch size, and the third dimension is feature dimension, what does the second dimension represent, and why does only the second dimension of the acoustic features change with the samples? Second, the IEMOCAP dataset consists of conversations containing a variable number of utterances, so in your input data, does a batch represent a batch of utterances or a batch of conversations?
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>
Hello, I have some questions about the input data. First, I see that when the original features you provided are loaded, all the three modal features have three dimensions, the first dimension is batch size, and the third dimension is feature dimension, what does the second dimension represent, and why does only the second dimension of the acoustic features change with the samples? Second, the IEMOCAP dataset consists of conversations containing a variable number of utterances, so in your input data, does a batch represent a batch of utterances or a batch of conversations?