Post Quantization TFLITE model

postQuantization.py

# save this file as postQuantization.py
def representative_dataset():
    for _ in range(100):
      data = np.random.rand(1, 320, 320, 3)
      yield [data.astype(np.float32)]

import numpy as np
import tensorflow as tf

saved_model_dir = "output/exported_models/tflite_infernce/saved_model"

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
converter.allow_custom_ops = True
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = representative_dataset
converter.inference_input_type = tf.uint8  # or tf.uint8
converter.inference_output_type = tf.uint8  # or tf.uint8
tflite_quant_model = converter.convert()

with tf.io.gfile.GFile(tf_lite_model_path, 'wb') as f:
  f.write(tflite_quant_model)