Skip to content

Yizong98/Dog_classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

dog-breed_classifier

dog-breed_classifier is a classifier that uses CNN(Concolutional Neural Network) plus transfer learning to do dog breed classification. When a human figure is detected, the classifier will output the most similar breed of dog to that person. If neither human nor dog is detected, the classifier will output 'An error in detection has just happened! '

Documentation

Install

Necessary Packages:

SK_learn

Numpy

Keras

Tensorflow

Matplotlib

OpenCV2

Jupyter Notebook

Usage Manual

  • Open the dog_app.ipynb with Jupyter Notebook
  • Put your testing images to the directory test_images.
  • Run all the cells in the file.
  • Follow the structure of the very last cell and you are good to classify your own images!
  • Carefully observe the results and analyze why such classification could be a difficult task.

License

dog-breed_classifier is Copyright © 2008-2018 Franz Bot. It is free software, and may be redistributed.