AN 1011: TinyML Applications in Altera FPGAs Using LiteRT for Microcontrollers

ID 848984
Date 4/07/2025
Public
Document Table of Contents

2.3.5. Saving and Loading Model

Once you train a highly accurate model, Altera recommends that you save the model data for future use. Training a model consumes a lot of time, and the final accuracy can vary with each session. By saving the trained model, you can efficiently load it whenever you need it.
# Save Model
model.save('lenet.keras')

# Load Model
model = tf.keras.models.load_model('lenet.keras')