Comments (10)
老师/同学,
你好,首先非常感谢对我们工作的关注。下面我将分两部分回答你的疑问:
(1)sutd视觉do干预模块在Code/model/VLCIR_sutd_GAFN_bertv3.py中,具体如下:
核心模块是:
(2)sutd语义do干预:
语言语义do模块贯穿于问题特征提取,视觉语言融合模块,以及最终推理过程。
首先在问题特征提取阶段,我们提取了subject,relation,object以及整个句子四种feature embedding,代码参考Code/1_preprocess_questions_oie.py;
然后,在视觉语言融合阶段,我们分别针对subject,relation,object以及整个句子这四种feature embedding,执行了相对应的操作,最终融合得到最终结果,具体代码如下:
from cmcir.
好的,十分感谢您的回复,这使得我对您和您团队的工作有了更加深入的理解,还有个问题,sutd数据集用readme所提供的链接(onedrive)进行下载zip内容并不全,请问可否重新提供一个国内可以下载的链接(例如百度网盘等),如果可以的话,万分感激!
from cmcir.
SUTD数据集不是我们团队的,我们无权提供下载链接,建议联系原作者。
from cmcir.
好的,谢谢您,最后一个问题,语义do干预的NWGM实现在代码具体的什么位置,视觉部分的基本上看您的回复找到了
from cmcir.
语义do干预不采用NWGM实现,只有视觉干预才采用NWGM实现。
from cmcir.
那您能具体指出一个地方的语义do干预的实现方法么,因为仔细阅读了Code/1_preprocess_questions_oie.py没有体会到do干预在哪里计算的
from cmcir.
1_preprocess_questions_oie.py目的是根据语义结构,提取subject,relation,object以及整个句子四种feature embedding,具体代码参见 https://github.com/YangLiu9208/CMCIR/blob/main/Code/preprocess/datautils/sutd_qa.py中process_questions_oie_keybert_bert2函数(2454行)。
from cmcir.
那么语义do干预操作体现在这个函数里的哪个具体操作呢,实在还是没找到,这个函数内容太多了
from cmcir.
您好!请问原文中公式5对应的先验概率p(z)统计计算的代码在哪儿呀,还有公式6中乘p(z)再累加对应的代码在哪儿呢,感谢!!(代码太多了,没找到555)
from cmcir.
请参考#2 (comment)
from cmcir.
Related Issues (3)
- Question about LGCAM HOT 5
- 执行预处理出错
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cmcir.