manlp-suda / hhmpn Goto Github PK
View Code? Open in Web Editor NEWMulti-modal Multi-label Emotion Recognition with Heterogeneous Hierarchical Message Passing
Multi-modal Multi-label Emotion Recognition with Heterogeneous Hierarchical Message Passing
你好~请问论文中说到的迭代次数T是指对哪些部分进行迭代呢?另外代码中的encoder和decoder分别对应论文模型中的哪些部分呢?
您好!很高兴接触到您的项目,我需要用到项目中的NEMu数据集,但是不同于MOSEI数据集,它是以job作为后缀的,如果要像pt后缀文件一样去使用它,我需要对它做一些什么处理呢?
您好,感谢您代码的开源,您提供了mosei_emotion_aligned_60.pkl,但是它不能用于运行报错如下:
Traceback (most recent call last):
File "main.py", line 129, in
main(opt)
File "main.py", line 49, in main
train_data,valid_data,test_data,label_adj_matrix,opt = process_data(data,opt)
File "/HHMPN-main/HHMPN/utils/data_loader.py", line 69, in process_data
label_adj_matrix = get_matrix(data['train']['tgt'],data['dict']['tgt'],t=0.2)
KeyError: 'tgt'
期待您的回复
你好,可以提供一下你的mosei的数据集吗?谢谢
我运行begin.sh文件时显示:bash:results/train_n_ly_3.log: No such file or directory,无法正常运行
Your job is very nice. I have some Question .
How to cast the feature vector to a node in graph, and how they are connected in implement?
作者你好,首先感谢你能开源这个非常棒的项目。我在使用你代码的途中对数据集这一块有些疑惑,我想咨询一下train_vaild_test.pt文件是如何生成的,是否有tool kit可以进行类似多模态数据集的处理(比如MELD, IEMOCAP等),谢谢!期待你的回复!
仔细阅读了代码,但和论文对不起来,不知道是什么部分没有太理解
encoder部分默认采用graph encoder, 但内部只看到单模态利用Transformer在做,没看到feature2feature有跨模态的部分
label2label没找到相应的部分
测试数据时,没有Label怎么进行Feature-to-Label和Label-to-Label的操作呢?
lamp.models文件中可以看到多模态信息是从encoder输入,从decoder输出的,decoder部分我理解的应该是实现了f-l, l-l, m-l三部分的结构,但是可能是我没有看到/或者是理解有误,如果用graph decoder, 那么会发现有f-l的部分用transformer decoder实现,m-l部分也有一个angle-fusion函数实现,好像唯独缺了l-l部分的实现。
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.