Comments (1)
I met the same issue. However, I counted the total number of predict_slots, real_slots and words. And found that they are equal. I went through codes and find the reason.
Here is why:
There is a LSTM unit in model. When using nn.utils.rnn.pack_padded_sequence and nn.utils.rnn.pad_packed_sequence, the data in the batch needs to be sorted from long to short. You can find the sorting code in utils/loader.py add_padding
However, the writer forgot to restore the order after predicting the slot and cause this issue.
So it is not a principle bug which may cause the entire results wrong, just a visualization bug~~
I will fix it soon with a PR. : )
from stackpropagation-slu.
Related Issues (8)
- 测试结果问题 HOT 2
- 为什么要把一个batch里面的sent展平成一个长序列呢?(LSTMEncoder和SelfAttention最后输出都是这样处理)
- 如何与BERT同时使用? HOT 1
- 关于模型选择的方法合理性的疑问 HOT 1
- bert embedding HOT 3
- 精度无法复现 HOT 1
- The Attention may need mask HOT 2
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 stackpropagation-slu.