Машинное обучение — Пример 1 — Классификация изображений с помощью CNN

import tensorflow as tf

from tensorflow.keras.datasets import cifar10
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.preprocessing.image import ImageDataGenerator

# Загружаем данные
(X_train, y_train), (X_test, y_test) = cifar10.load_data()

# Нормализуем данные
X_train = X_train.astype('float32') / 255.0
X_test = X_test.astype('float32') / 255.0

# Преобразуем метки в one-hot encoding
y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)

# Создаем генератор аугментации данных
datagen = ImageDataGenerator(
    rotation_range=15,
    width_shift_range=0.1,
    height_shift_range=0.1,
    horizontal_flip=True
)
datagen.fit(X_train)

# Создаем модель
model = Sequential([
    Conv2D(32, (3, 3), padding='same', activation='relu', input_shape=(32, 32, 3)),
    BatchNormalization(),
    Conv2D(32, (3, 3), padding='same', activation='relu'),
    BatchNormalization(),
    MaxPooling2D(pool_size=(2, 2)),
    Dropout(0.25),
    
    Conv2D(64, (3, 3), padding='same', activation='relu'),
    BatchNormalization(),
    Conv2D(64, (3, 3), padding='same', activation='relu'),
    BatchNormalization(),
    MaxPooling2D(pool_size=(2, 2)),
    Dropout(0.25),
    
    Conv2D(128, (3, 3), padding='same', activation='relu'),
    BatchNormalization(),
    Conv2D(128, (3, 3), padding='same', activation='relu'),
    BatchNormalization(),
    MaxPooling2D(pool_size=(2, 2)),
    Dropout(0.25),
    
    Flatten(),
    Dense(512, activation='relu'),
    BatchNormalization(),
    Dropout(0.5),
    Dense(10, activation='softmax')
])

# Компилируем модель
model.compile(
    optimizer='adam',
    loss='categorical_crossentropy',
    metrics=['accuracy']
)

# Обучаем модель
history = model.fit(
    datagen.flow(X_train, y_train, batch_size=64),
    epochs=50,
    validation_data=(X_test, y_test),
    steps_per_epoch=X_train.shape[0] // 64
)

# Оцениваем модель
test_loss, test_accuracy = model.evaluate(X_test, y_test)
print(f"Точность на тестовых данных: {test_accuracy:.4f}")

# Сохраняем модель
model.save('cifar10_cnn_model.h5')