遷移學習與微調

import numpy as np
import keras
from keras import layers
import tensorflow_datasets as tfds
import matplotlib.pyplot as plt

layer = keras.layers.Dense(3)
layer.build((None, 4))  # Create the weights

print("weights:", len(layer.weights))
print("trainable_weights:", len(layer.trainable_weights))
print("non_trainable_weights:", len(layer.non_trainable_weights))

layer = keras.layers.BatchNormalization()
layer.build((None, 4))  # Create the weights

print("weights:", len(layer.weights))
print("trainable_weights:", len(layer.trainable_weights))
print("non_trainable_weights:", len(layer.non_trainable_weights))

layer = keras.layers.Dense(3)
layer.build((None, 4))  # Create the weights
layer.trainable = False  # Freeze the layer

print("weights:", len(layer.weights))
print("trainable_weights:", len(layer.trainable_weights))
print("non_trainable_weights:", len(layer.non_trainable_weights))

# Make a model with 2 layers
layer1 = keras.layers.Dense(3, activation="relu")
layer2 = keras.layers.Dense(3, activation="sigmoid")
model = keras.Sequential([keras.Input(shape=(3,)), layer1, layer2])

# Freeze the first layer
layer1.trainable = False

# Keep a copy of the weights of layer1 for later reference
initial_layer1_weights_values = layer1.get_weights()

# Train the model
model.compile(optimizer="adam", loss="mse")
model.fit(np.random.random((2, 3)), np.random.random((2, 3)))

# Check that the weights of layer1 have not changed during training
final_layer1_weights_values = layer1.get_weights()
np.testing.assert_allclose(
    initial_layer1_weights_values[0], final_layer1_weights_values[0]
)
np.testing.assert_allclose(
    initial_layer1_weights_values[1], final_layer1_weights_values[1]
)

inner_model = keras.Sequential(
    [
        keras.Input(shape=(3,)),
        keras.layers.Dense(3, activation="relu"),
        keras.layers.Dense(3, activation="relu"),
    ]
)

model = keras.Sequential(
    [
        keras.Input(shape=(3,)),
        inner_model,
        keras.layers.Dense(3, activation="sigmoid"),
    ]
)

model.trainable = False  # Freeze the outer model

assert inner_model.trainable == False  # All layers in `model` are now frozen
assert inner_model.layers[0].trainable == False  # `trainable` is propagated recursively

base_model = keras.applications.Xception(
    weights='imagenet',  # Load weights pre-trained on ImageNet.
    input_shape=(150, 150, 3),
    include_top=False)  # Do not include the ImageNet classifier at the top.

base_model.trainable = False

inputs = keras.Input(shape=(150, 150, 3))
# We make sure that the base_model is running in inference mode here,
# by passing `training=False`. This is important for fine-tuning, as you will
# learn in a few paragraphs.
x = base_model(inputs, training=False)
# Convert features of shape `base_model.output_shape[1:]` to vectors
x = keras.layers.GlobalAveragePooling2D()(x)
# A Dense classifier with a single unit (binary classification)
outputs = keras.layers.Dense(1)(x)
model = keras.Model(inputs, outputs)

model.compile(optimizer=keras.optimizers.Adam(),
              loss=keras.losses.BinaryCrossentropy(from_logits=True),
              metrics=[keras.metrics.BinaryAccuracy()])
model.fit(new_dataset, epochs=20, callbacks=..., validation_data=...)

# Unfreeze the base model
base_model.trainable = True

# It's important to recompile your model after you make any changes
# to the `trainable` attribute of any inner layer, so that your changes
# are take into account
model.compile(optimizer=keras.optimizers.Adam(1e-5),  # Very low learning rate
              loss=keras.losses.BinaryCrossentropy(from_logits=True),
              metrics=[keras.metrics.BinaryAccuracy()])

# Train end-to-end. Be careful to stop before you overfit!
model.fit(new_dataset, epochs=10, callbacks=..., validation_data=...)

tfds.disable_progress_bar()

train_ds, validation_ds, test_ds = tfds.load(
    "cats_vs_dogs",
    # Reserve 10% for validation and 10% for test
    split=["train[:40%]", "train[40%:50%]", "train[50%:60%]"],
    as_supervised=True,  # Include labels
)

print(f"Number of training samples: {train_ds.cardinality()}")
print(f"Number of validation samples: {validation_ds.cardinality()}")
print(f"Number of test samples: {test_ds.cardinality()}")

plt.figure(figsize=(10, 10))
for i, (image, label) in enumerate(train_ds.take(9)):
    ax = plt.subplot(3, 3, i + 1)
    plt.imshow(image)
    plt.title(int(label))
    plt.axis("off")

resize_fn = keras.layers.Resizing(150, 150)

train_ds = train_ds.map(lambda x, y: (resize_fn(x), y))
validation_ds = validation_ds.map(lambda x, y: (resize_fn(x), y))
test_ds = test_ds.map(lambda x, y: (resize_fn(x), y))

augmentation_layers = [
    layers.RandomFlip("horizontal"),
    layers.RandomRotation(0.1),
]


def data_augmentation(x):
    for layer in augmentation_layers:
        x = layer(x)
    return x


train_ds = train_ds.map(lambda x, y: (data_augmentation(x), y))

from tensorflow import data as tf_data

batch_size = 64

train_ds = train_ds.batch(batch_size).prefetch(tf_data.AUTOTUNE).cache()
validation_ds = validation_ds.batch(batch_size).prefetch(tf_data.AUTOTUNE).cache()
test_ds = test_ds.batch(batch_size).prefetch(tf_data.AUTOTUNE).cache()

for images, labels in train_ds.take(1):
    plt.figure(figsize=(10, 10))
    first_image = images[0]
    for i in range(9):
        ax = plt.subplot(3, 3, i + 1)
        augmented_image = data_augmentation(np.expand_dims(first_image, 0))
        plt.imshow(np.array(augmented_image[0]).astype("int32"))
        plt.title(int(labels[0]))
        plt.axis("off")

base_model = keras.applications.Xception(
    weights="imagenet",  # Load weights pre-trained on ImageNet.
    input_shape=(150, 150, 3),
    include_top=False,
)  # Do not include the ImageNet classifier at the top.

# Freeze the base_model
base_model.trainable = False

# Create new model on top
inputs = keras.Input(shape=(150, 150, 3))

# Pre-trained Xception weights requires that input be scaled
# from (0, 255) to a range of (-1., +1.), the rescaling layer
# outputs: `(inputs * scale) + offset`
scale_layer = keras.layers.Rescaling(scale=1 / 127.5, offset=-1)
x = scale_layer(inputs)

# The base model contains batchnorm layers. We want to keep them in inference mode
# when we unfreeze the base model for fine-tuning, so we make sure that the
# base_model is running in inference mode here.
x = base_model(x, training=False)
x = keras.layers.GlobalAveragePooling2D()(x)
x = keras.layers.Dropout(0.2)(x)  # Regularize with dropout
outputs = keras.layers.Dense(1)(x)
model = keras.Model(inputs, outputs)

model.summary(show_trainable=True)

model.compile(
    optimizer=keras.optimizers.Adam(),
    loss=keras.losses.BinaryCrossentropy(from_logits=True),
    metrics=[keras.metrics.BinaryAccuracy()],
)

epochs = 2
print("Fitting the top layer of the model")
model.fit(train_ds, epochs=epochs, validation_data=validation_ds)

# Unfreeze the base_model. Note that it keeps running in inference mode
# since we passed `training=False` when calling it. This means that
# the batchnorm layers will not update their batch statistics.
# This prevents the batchnorm layers from undoing all the training
# we've done so far.
base_model.trainable = True
model.summary(show_trainable=True)

model.compile(
    optimizer=keras.optimizers.Adam(1e-5),  # Low learning rate
    loss=keras.losses.BinaryCrossentropy(from_logits=True),
    metrics=[keras.metrics.BinaryAccuracy()],
)

epochs = 1
print("Fitting the end-to-end model")
model.fit(train_ds, epochs=epochs, validation_data=validation_ds)

print("Test dataset evaluation")
model.evaluate(test_ds)