CIFAR10 machine learning example using Tensorflow & Keras
Tested with Tensorflow ver 1.12
Demonstrates the following:
- how to create a simple CNN using a Keras sequential model
- how load the CIFAR10 dataset and normalize the image values.
- how to set up Keras callbacks for Tensorboard logging, early stopping and checkpoint saving.
- how to compile, train, evaluate the model.
- how to make predictions with the trained model.
- how to save the Keras model as HDF5 and JSON formats.
- how to freeze the TF graph to a protobuf file from Keras
Jupyter notebook here.
Python source code here.