訓練後の整数量子化

import logging
logging.getLogger("tensorflow").setLevel(logging.DEBUG)

import tensorflow as tf
import numpy as np
print("TensorFlow version: ", tf.__version__)

# Load MNIST dataset
mnist = tf.keras.datasets.mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

# Normalize the input image so that each pixel value is between 0 to 1.
train_images = train_images.astype(np.float32) / 255.0
test_images = test_images.astype(np.float32) / 255.0

# Define the model architecture
model = tf.keras.Sequential([
  tf.keras.layers.InputLayer(input_shape=(28, 28)),
  tf.keras.layers.Reshape(target_shape=(28, 28, 1)),
  tf.keras.layers.Conv2D(filters=12, kernel_size=(3, 3), activation='relu'),
  tf.keras.layers.MaxPooling2D(pool_size=(2, 2)),
  tf.keras.layers.Flatten(),
  tf.keras.layers.Dense(10)
])

# Train the digit classification model
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(
                  from_logits=True),
              metrics=['accuracy'])
model.fit(
  train_images,
  train_labels,
  epochs=5,
  validation_data=(test_images, test_labels)
)

converter = tf.lite.TFLiteConverter.from_keras_model(model)

tflite_model = converter.convert()

converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.optimizations = [tf.lite.Optimize.DEFAULT]

tflite_model_quant = converter.convert()

def representative_data_gen():
  for input_value in tf.data.Dataset.from_tensor_slices(train_images).batch(1).take(100):
    # Model has only one input so each data point has one element.
    yield [input_value]

converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = representative_data_gen

tflite_model_quant = converter.convert()

interpreter = tf.lite.Interpreter(model_content=tflite_model_quant)
input_type = interpreter.get_input_details()[0]['dtype']
print('input: ', input_type)
output_type = interpreter.get_output_details()[0]['dtype']
print('output: ', output_type)

def representative_data_gen():
  for input_value in tf.data.Dataset.from_tensor_slices(train_images).batch(1).take(100):
    yield [input_value]

converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = representative_data_gen
# Ensure that if any ops can't be quantized, the converter throws an error
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
# Set the input and output tensors to uint8 (APIs added in r2.3)
converter.inference_input_type = tf.uint8
converter.inference_output_type = tf.uint8

tflite_model_quant = converter.convert()

interpreter = tf.lite.Interpreter(model_content=tflite_model_quant)
input_type = interpreter.get_input_details()[0]['dtype']
print('input: ', input_type)
output_type = interpreter.get_output_details()[0]['dtype']
print('output: ', output_type)

import pathlib

tflite_models_dir = pathlib.Path("/tmp/mnist_tflite_models/")
tflite_models_dir.mkdir(exist_ok=True, parents=True)

# Save the unquantized/float model:
tflite_model_file = tflite_models_dir/"mnist_model.tflite"
tflite_model_file.write_bytes(tflite_model)
# Save the quantized model:
tflite_model_quant_file = tflite_models_dir/"mnist_model_quant.tflite"
tflite_model_quant_file.write_bytes(tflite_model_quant)

# Helper function to run inference on a TFLite model
def run_tflite_model(tflite_file, test_image_indices):
  global test_images

  # Initialize the interpreter
  interpreter = tf.lite.Interpreter(model_path=str(tflite_file))
  interpreter.allocate_tensors()

  input_details = interpreter.get_input_details()[0]
  output_details = interpreter.get_output_details()[0]

  predictions = np.zeros((len(test_image_indices),), dtype=int)
  for i, test_image_index in enumerate(test_image_indices):
    test_image = test_images[test_image_index]
    test_label = test_labels[test_image_index]

    # Check if the input type is quantized, then rescale input data to uint8
    if input_details['dtype'] == np.uint8:
      input_scale, input_zero_point = input_details["quantization"]
      test_image = test_image / input_scale + input_zero_point

    test_image = np.expand_dims(test_image, axis=0).astype(input_details["dtype"])
    interpreter.set_tensor(input_details["index"], test_image)
    interpreter.invoke()
    output = interpreter.get_tensor(output_details["index"])[0]

    predictions[i] = output.argmax()

  return predictions

import matplotlib.pylab as plt

# Change this to test a different image
test_image_index = 1

## Helper function to test the models on one image
def test_model(tflite_file, test_image_index, model_type):
  global test_labels

  predictions = run_tflite_model(tflite_file, [test_image_index])

  plt.imshow(test_images[test_image_index])
  template = model_type + " Model \n True:{true}, Predicted:{predict}"
  _ = plt.title(template.format(true= str(test_labels[test_image_index]), predict=str(predictions[0])))
  plt.grid(False)

test_model(tflite_model_file, test_image_index, model_type="Float")

test_model(tflite_model_quant_file, test_image_index, model_type="Quantized")

# Helper function to evaluate a TFLite model on all images
def evaluate_model(tflite_file, model_type):
  global test_images
  global test_labels

  test_image_indices = range(test_images.shape[0])
  predictions = run_tflite_model(tflite_file, test_image_indices)

  accuracy = (np.sum(test_labels== predictions) * 100) / len(test_images)

  print('%s model accuracy is %.4f%% (Number of test samples=%d)' % (
      model_type, accuracy, len(test_images)))

evaluate_model(tflite_model_file, model_type="Float")

evaluate_model(tflite_model_quant_file, model_type="Quantized")