This program classifies images from "from Software games". It creates an image classifier using a tf.keras.Sequential model, and loads data using tf.keras.utils.image_dataset_from_directory. The code is practical as it can be scaled up to larger data sets.
In this code we: Efficiently load a dataset. Apply techniques to mitigate overfitting, as well as using data augmentation and dropout.
Flow: input pipeline model Train the model Test the model Analysis.