Comments (2)
论文中CMX的算法中other tokens抱歉产生了误解,这里有一个从前往后遍历的trick,会是和自己之后的其他token做计算。并且,如果不用矩阵mask,很多相似token是直接丢失的,这样后面的resampler的merge也就无从说起了。另外至于最后一个token存在的问题,其实只是一个选择的问题,如果存在和它很相似的token,我们选择了保留偏后的token,而非靠前的token。
from monkey.
论文中CMX的算法中other tokens抱歉产生了误解,这里有一个从前往后遍历的trick,会是和自己之后的其他token做计算。并且,如果不用矩阵mask,很多相似token是直接丢失的,这样后面的resampler的merge也就无从说起了。另外至于最后一个token存在的问题,其实只是一个选择的问题,如果存在和它很相似的token,我们选择了保留偏后的token,而非靠前的token。
感谢解答,这样确实是更加合理的做法,采用下三角mask的做法能够正好实现这一点👍
from monkey.
Related Issues (20)
- AttributeError: 'Linear' object has no attribute 'bias'
- infer效果不符合预期,希望输出text但是和论文结果相差很远,请问是我代码出问题了吗?麻烦帮忙看一下,感谢🙏 HOT 4
- textmonkey论文里描述的是"sliding window"是用于切块448大小的时候导致的不连续性 HOT 1
- 运行inference.py报错,不知道什么问题 HOT 1
- Code of Resampler is not used in Monkey? HOT 3
- 使用textmonkey的脚本,进行一阶段训练,loss为0 HOT 1
- Mini-Monkey的训练数据 HOT 7
- datagenration- 30k of your samples are being preprocessed incorrectly HOT 1
- 无
- 请问你minimonkey论文中KIE数据集这些指标是怎么测的呀? HOT 2
- 评估结果 HOT 1
- Miini-monkey pre-training scripts.
- mini-monkey是否支持CPU部署? HOT 1
- 如何微调自己的数据,用在自己的项目上,在自己的项目上效果不是很好,如何制作数据 HOT 1
- 评估问题
- mini monkey 评估ocrbench指标和论文对不上 HOT 1
- 有关多模态大模型相关问题,欢迎加入多模态群,进行交流 HOT 1
- 如何提问实现OCR提取图片上的所有文字? HOT 1
- 关于MASC即插即用的疑惑 HOT 4
- How to use TextMonkey to inference HOT 1
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 monkey.