This tutorial shows how to classify cats or dogs from images. It builds an image classifier using a tf.keras.Sequential model and load data using tf.keras.preprocessing.image.ImageDataGenerator.
You will get some practical experience and develop intuition for the following concepts:
- Building data input pipelines using the tf.keras.preprocessing.image.ImageDataGenerator class to efficiently work with data on disk to use with the model.
- Overfitting - How to identify and prevent it.
- Data augmentation and dropout - Key techniques to fight overfitting in computer vision tasks to incorporate into the data pipeline and image classifier model.
This tutorial was conducted as a part of an initiative for TensorFlow All Around from Google.