Algorithm for a Dog Identification App
The goal of this project was to build a pipeline that can be used within a web or mobile app to process real-world, user-supplied images. Given an image of a dog, the algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed.
I used python and keras interface from tensorflow to build a Convolutional Neural Networks (CNN) to classify dog breeds. The model was trained on the Dog Breed Identification dataset. The dataset contains 8351 dog images and 133 breeds.
Check out the project on GitHub.