model_h5_to_tflite8.py

converter = tf.lite.TFLiteConverter.from_keras_model(model_for_export)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
quantized_and_pruned_tflite_model = converter.convert()

_, quantized_and_pruned_tflite_file = tempfile.mkstemp('.tflite')

with open(quantized_and_pruned_tflite_file, 'wb') as f:
  f.write(quantized_and_pruned_tflite_model)

print('Saved quantized and pruned TFLite model to:', quantized_and_pruned_tflite_file)

print("Size of gzipped baseline Keras model: %.2f bytes" % (get_gzipped_model_size(keras_file)))
print("Size of gzipped pruned and quantized TFlite model: %.2f bytes" % (get_gzipped_model_size(quantized_and_pruned_tflite_file)))