pipeline/quantization.py

#For reducing the size of model while keeping accuracy same for faster inference
import tensorflow as tf
from tensorflow.keras.models import load_model

# Model Loading
model = load_model("models/bilstm_fake_news_model.h5")

# Conversion with TFLiteConverter
converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.target_spec.supported_types = [tf.float16]

converter.target_spec.supported_ops = [
    tf.lite.OpsSet.TFLITE_BUILTINS,      
    tf.lite.OpsSet.SELECT_TF_OPS
]
converter._experimental_lower_tensor_list_ops = False  

tflite_model = converter.convert()

# Saving
with open("models/bilstm_fake_news_float16.tflite", "wb") as f:
    f.write(tflite_model)