卷积神经网络可以实现两类图像识别分类功能的代码

1. 图像分类

下面是一个简单的卷积神经网络，用于图像分类任务：

import tensorflow as tf

# 定义卷积神经网络，包括卷积层、池化层和全连接层
model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(10)
])

# 编译模型
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

# 加载数据集
mnist = tf.keras.datasets.mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

# 转换数据集格式
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images / 255.0
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images / 255.0

# 训练模型
model.fit(train_images, train_labels, epochs=5)

# 评估模型
test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)
print('Test accuracy:', test_acc)

2. 目标检测

下面是一个简单的卷积神经网络，用于目标检测任务：

import tensorflow as tf

# 定义卷积神经网络，包括卷积层、池化层和全连接层
model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(16, (3, 3), activation='relu', input_shape=(None, None, 3)),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(4) # 四个坐标值分别表示目标框的左上角和右下角坐标
])

# 编译模型
model.compile(optimizer='adam',
              loss='mse')

# 加载数据集
dataset = tf.data.Dataset.from_tensor_slices((train_images, train_labels))

# 定义数据预处理函数
def preprocess_image(image, labels):
    # 对图像进行归一化和缩放
    image = tf.cast(image, tf.float32) / 255.0
    image = tf.image.resize(image, (224, 224))
    return image, labels

# 对数据集进行预处理和打乱
dataset = dataset.map(preprocess_image).shuffle(buffer_size=1024)

# 训练模型
model.fit(dataset.batch(32), epochs=10)

# 评估模型
test_loss = model.evaluate(test_images, test_labels, verbose=2)
print('Test loss:', test_loss)