🐶 Dog-Vision-Neural-Network

This notebook builds and end-to-end multi-class image classifier using TensorFlow 2.0 and TensorFlow Hub.

This kind of problem is called multi-class image classification. It's multi-class because we're trying to classify mutliple different breeds of dog. If we were only trying to classify dogs versus cats, it would be called binary classification.

Multi-class image classification is an important problem because it's the same kind of technology Tesla uses in their self-driving cars or Airbnb uses in atuomatically adding information to their listings.

Data

The data we're using is from Kaggle's dog breed identification competition: https://www.kaggle.com/c/dog-breed-identification/data

In this notebook I've did the following:

1. Get data ready (download from Kaggle, store, import).
2. Prepare the data (preprocessing, the 3 sets, X & y).
3. Choose and fit/train a model (TensorFlow Hub, tf.keras.applications, TensorBoard, EarlyStopping).
4. Evaluating a model (making predictions, comparing them with the ground truth labels).
5. Improve the model through experimentation (start with 1000 images, make sure it works, increase the number of images).
6. Save, sharing and reloading your model.