Comments (3)
It is a tricky function. The probability for each class will get decreased or leaked if one additional dummy-class is considered. This function will be working for the case where one primary capsule is noisy and it doesn't contribute to any capsules in the subsequent layers.
from capsule_text_classification.
Thanks, Is that
from capsule_text_classification.
Correct.
from capsule_text_classification.
Related Issues (20)
- Library requirements HOT 4
- 为什么我得不到你论文里面的结果? HOT 1
- How do you split the dataset in the paper? HOT 1
- main.py: error: unrecognized arguments: -- model_type CNN --learning_rate 0.0005
- py-2 to py-3, int(num_classes)
- About CapsuleConv, FullyConnected layers. HOT 1
- hd5 file for other datasets, such as MR
- the dataset is valid! HOT 2
- For a single label task, how do you handle the output of the model ? HOT 1
- got an error HOT 5
- layer.py 101行 的 激活函数怎么理解? HOT 2
- Orphan Category HOT 1
- The loss don't change
- 数据在哪里获得
- "Coefficients Amendmen" strategy isn't implement in code
- 文本分类相关问题 HOT 3
- ValueError: num_outputs should be int or long, got 9.
- pytorch实现的代码 HOT 2
- 数据集
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 capsule_text_classification.