将 TensorFlow 模型导出为 LiteRT

import tensorflow as tf

# Convert the model
saved_model_dir = "/path/to/tf/model/in/saved_model/format"
converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
tflite_model = converter.convert()

# Save the model
with open("model.tflite", "wb") as f:
    f.write(tflite_model)

import tensorflow as tf

# Create a model using high-level tf.keras.* APIs
model = tf.keras.models.Sequential([
    tf.keras.layers.Dense(units=1, input_shape=[1]),
    tf.keras.layers.Dense(units=16, activation='relu'),
    tf.keras.layers.Dense(units=1)
])

# Compile and train the model
model.compile(optimizer='sgd', loss='mean_squared_error')
model.fit(x=[-1, 0, 1], y=[-3, -1, 1], epochs=5)

# Convert the model to LiteRT
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()

# Save the model
with open('model.tflite', 'wb') as f:
    f.write(tflite_model)

import tensorflow as tf

converter = tf.lite.TFLiteConverter.from_saved_model(exp_model_path)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
converter.optimizations = [tf.lite.Optimize.DEFAULT]

tflite_model = converter.convert()
save_name = 'quantized_model.tflite'

print('Saving Dynamic Quantized LiteRT model')

with open(save_name, 'wb') as f:
    f.write(tflite_model)

import tensorflow as tf

def representative_dataset():
    for data in dataset:
        yield {"image": data.image, "bias": data.bias}

saved_model_dir = "/path/to/saved/model"

# Load the model
converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
converter.optimizations = [tf.lite.Optimize.DEFAULT]

# Set the representative dataset for quantization
converter.representative_dataset = representative_dataset

# For full integer quantization, set target_spec to TFLITE_BUILTINS_INT8
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
converter.inference_input_type = tf.int8   # or tf.uint8
converter.inference_output_type = tf.int8  # or tf.uint8

# Convert the model
tflite_quant_model = converter.convert()
save_name = 'quantized_model_int8.tflite'

print('Saving Quantized LiteRT model')

with open(save_name, 'wb') as f:
    f.write(tflite_quant_model)

tflite_convert \
  --saved_model_dir=/tmp/mobilenet_saved_model \
  --output_file=/tmp/mobilenet.tflite

tflite_convert \
  --keras_model_file=/tmp/mobilenet_keras_model.h5 \
  --output_file=/tmp/mobilenet.tflite