Comments (1)
Wow, I've never seen it "forget" this badly.
That said, even at iteration 165, you see the training accuracy is at 0.9845 - while the validation accuracy is stuck at 0.9613 (pretty good!). The network is starting to overfit the input data, but the performance on the testing data (which is unseen by the network during the training process) is not improving anymore.
At somewhere around that point you need to stop the training - I have not programmed an automatic stopping mechanism for this.
from deepspell.
Related Issues (20)
- Memory Issue HOT 7
- Not reaching quoted accuracy HOT 2
- Trailing Periods HOT 4
- char_frequency.json is missing HOT 5
- train_speller() HOT 1
- preprocesses_split_lines4(): gensim Deprecation Warning + Error HOT 1
- real word error
- use for two language! HOT 5
- unable to generate char_frequency.json
- How the prediction is working?
- getting wrong output
- Hi, could you please provide your last checkpoint ? It would be of great help
- time out error
- is there any released model for downloading ? HOT 1
- Running on Tensorflow Backend
- tensorflow or theano? HOT 2
- usage train dataset with errors
- optimal params for training
- continue training after crash 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 deepspell.