Skip to content
forked from lukas/ml-class

Materials for class on machine learning/deep learning using scikit-learn, tensorflow and keras

License

Notifications You must be signed in to change notification settings

richtox/ml-class

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Training

python train_emotion_classifier.py

Testing

python run_classifier.py test.jpg

Things to try:

Look at the data!

  • How is it distributed? How well would a random model do?
  • Can the model learn on a tiny subset of the data?

Better models

  • Better architecture

Data cleanup

  • Normalize

Data generation

Reduce learning rate on plateau

Find more training data online?

Anything else?

About

Materials for class on machine learning/deep learning using scikit-learn, tensorflow and keras

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Jupyter Notebook 80.1%
  • Python 19.9%