Udacity data science nanodegree project 4
- Libraries used
- Project Inspiration
- File Descriptions
- Data Insights
- Licensing, Authors, and Acknowledgements
Python version 3.0. Plugins and imports used were: Keras, Pandas, MatplotLib. Libraries:Scikit-learn, numpy, matplotlib, os, glob
Have you ever had a time that when we walk on street or look on instagram, seen a cute dog and don’t know what breed it is. This is exhuasting for many of us, we are all dog lovers, so dog breed classifier comes handy for us. Why dog breed classifier is challenging? These 2 sets of dog comaprsion may give us a taste of it. Human eyes barely can tell the differences.
dog_breed_classifier.ipynb : Jupyter notebook containing all the codes and results
dog_breed_classifier.html : Jupyter notebook in hmtl form containing all the codes and results
saved_models : A folder contains 3 models I trained, CNN from scratch, vgg16 CNN, and ResNet-50 CNN
Dog_img : A folder contains all the images I used for the test from internet
Asset : Pictures I used for write ReadMe file
I build a CNN using transfer learning to classify dog breeds that can reach 85% accuracy on test data. Then:
what is an CNN, what is VGG16? etc
How this classifier works?
Before we dive into details, take a look of our dataset, human faces
Dog breed image barplot to understand how our data distributed among breeds
How the classifier performs on test images?
How the classifer performs in real life?
At the end, using ResNet-50 transfer learning we build a CNN can reach 85% test accuracy, which is perfect for us. Also there are some posiible improvements, all the detials is discussed in this post
Authors: here