DenseNet121模型实现26个英文字母识别任务

import numpy as np
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D, BatchNormalization
from tensorflow.keras.layers import Input, concatenate
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.regularizers import l2
from tensorflow.keras.callbacks import EarlyStopping
from sklearn.model_selection import train_test_split
from PIL import Image

batch_size = 128 # 批量大小
num_classes = 26 # 分类数目
epochs = 50 # 训练轮数

# 加载数据集
def load_dataset(path):
    with np.load(path) as data:
        X_train = data['X_train']
        y_train = data['y_train']
        X_test = data['X_test']
        y_test = data['y_test']
    return (X_train, y_train), (X_test, y_test)
# 加载数据集并进行归一化处理
def preprocess_data(X_train, y_train, X_test, y_test):
    # 将图像矩阵归一化到0-1之间
    X_train = X_train.astype('float32') / 255.
    X_test = X_test.astype('float32') / 255.
    # 将标签矩阵转换为one-hot编码
    y_train = keras.utils.to_categorical(y_train, num_classes)
    y_test = keras.utils.to_categorical(y_test, num_classes)
    return X_train, y_train, X_test, y_test
# 加载训练和测试数据
(X_train_val, y_train_val), (X_test, y_test) = load_dataset('/data/emnist/mnist.npz')
# 划分训练集和验证集
X_train, X_val, y_train, y_val = train_test_split(X_train_val, y_train_val,
                                                  test_size=0.2, random_state=42)
# 对数据进行归一化处理
X_train, y_train, X_val, y_val = preprocess_data(X_train, y_train, X_val, y_val)
X_test, y_test = preprocess_data(X_test, y_test, [], [])

# 定义dense_block函数
def dense_block(x, blocks, growth_rate):
    for i in range(blocks):
        x1 = BatchNormalization()(x)
        x1 = Conv2D(growth_rate * 4, (1, 1), padding='same', activation='relu',
                    kernel_initializer='he_normal')(x1)
        x1 = BatchNormalization()(x1)
        x1 = Conv2D(growth_rate, (3, 3), padding='same', activation='relu',
                    kernel_initializer='he_normal')(x1)
        x = concatenate([x, x1])
    return x
# 定义transition_layer函数
def transition_layer(x, reduction):
    x = BatchNormalization()(x)
    x = Conv2D(int(x.shape.as_list()[-1] * reduction), (1, 1), activation='relu',
                kernel_initializer='he_normal')(x)
    x = MaxPooling2D((2, 2), strides=(2, 2))(x)
    return x
# 构建DenseNet网络
def DenseNet(input_shape, num_classes, dense_blocks=3, dense_layers=-1,
             growth_rate=12, reduction=0.5, dropout_rate=0.0, weight_decay=1e-4):
    # 指定初始通道数和块数
    depth = dense_blocks * dense_layers + 2
    in_channels = 2 * growth_rate
    inputs = Input(shape=input_shape)
    # 第一层卷积
    x = Conv2D(in_channels, (3, 3), padding='same', use_bias=False,
               kernel_initializer='he_normal')(inputs)
    # 堆叠密集块和过渡层
    for i in range(dense_blocks):
        x = dense_block(x, dense_layers, growth_rate)
        in_channels += growth_rate * dense_layers
        if i != dense_blocks - 1:
            x = transition_layer(x, reduction)
    # 全局平均池化
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = GlobalAveragePooling2D()(x)
    # 输出层
    outputs = Dense(num_classes, activation='softmax',
                     kernel_initializer='he_normal')(x)
    # 定义模型
    model = Model(inputs=inputs, outputs=outputs, name='DenseNet')
    return model
# 构建DenseNet121网络
model = DenseNet(input_shape=(28, 28, 1), num_classes=num_classes, dense_blocks=3,
           dense_layers=4, growth_rate=12, reduction=0.5, dropout_rate=0.0,
           weight_decay=1e-4)
# 指定优化器、损失函数和评价指标
opt = Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08)
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
# 输出模型概况
model.summary()

# 定义早停策略
earlystop = EarlyStopping(monitor='val_loss', min_delta=0.0001, patience=5,
                          verbose=1, mode='auto', restore_best_weights=True)
# 训练模型
history = model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs,
          verbose=1, validation_data=(X_val, y_val), callbacks=[earlystop])

# 对模型进行评估
score = model.evaluate(X_test, y_test, verbose=0)
# 计算各项指标
test_accuracy = score[1]
print('Test accuracy:', test_accuracy)
# 保存模型
model.save('densenet121.h5')