卷积神经网络（LeNet）_卷积神经网络(lenet)-CSDN博客

本文链接：https://blog.csdn.net/qq_43656233/article/details/106095357

本文介绍了一个使用TensorFlow和Keras构建的卷积神经网络（CNN）模型，用于Fashion MNIST数据集的手写服装识别任务。模型包括多个卷积层、池化层和全连接层，并使用SGD优化器进行训练。通过5轮训练，模型在验证集上取得了良好的性能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import tensorflow as tf

net = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(filters=6, kernel_size=5, activation='sigmoid', input_shape=(28, 28, 1)),
    tf.keras.layers.MaxPool2D(pool_size=2, strides=2),
    tf.keras.layers.Conv2D(filters=16, kernel_size=5, activation='sigmoid'),
    tf.keras.layers.MaxPool2D(pool_size=2, strides=2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(120, activation='sigmoid'),
    tf.keras.layers.Dense(84, activation='sigmoid'),
    tf.keras.layers.Dense(10, activation='sigmoid')
])

# 测试网络结构
# X = tf.random.uniform((1, 28, 28, 1))
# for layer in net.layers:
#     X = layer(X)
#     print(layer.name, 'output shape\t', X.shape)

fashion_mnist = tf.keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

# 为数据集增加一维
train_images = tf.reshape(train_images, (train_images.shape[0], train_images.shape[1], train_images.shape[2], 1))
print(train_images.shape)
test_images = tf.reshape(test_images, (test_images.shape[0], test_images.shape[1], test_images.shape[2], 1))
print(test_images.shape)

optimizer = tf.keras.optimizers.SGD(learning_rate=0.9, momentum=0.0, nesterov=False)

net.compile(optimizer=optimizer,
            loss='sparse_categorical_crossentropy',
            metrics=['accuracy'])

train_score = []
test_score = []

# verbose：该参数的值控制日志显示的方式
# verbose=0 不在标准输出流输出日志信息
# verbose=1 输出进度条记录（默认）
# verbose=2 每个epoch输出一行记录
net.fit(train_images, train_labels, epochs=5, validation_split=0.1, verbose=2)
net.evaluate(test_images, test_labels, verbose=2)