LeNet-5训练神经网络训练

本文主要是介绍LeNet-5训练神经网络训练，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

LeNet-5训练

导包

import tensorflow as tf from tensorflow.keras import layers, models, datasets, optimizers 

加载Fashion-MNIST数据集 

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

归一化像素值到[0, 1]区间 

train_images = train_images.astype("float32") / 255 test_images = test_images.astype("float32") / 255

对标签进行分类编码 

train_labels = tf.keras.utils.to_categorical(train_labels, 10) test_labels = tf.keras.utils.to_categorical(test_labels, 10)

定义LeNet-5模型

model = models.Sequential([ layers.Conv2D(6, (5, 5), activation='relu', input_shape=(28, 28, 1)), layers.AveragePooling2D((2, 2)), layers.Conv2D(16, (5, 5), activation='relu'), layers.AveragePooling2D((2, 2)), layers.Conv2D(120, (3, 3), activation='relu', padding='valid'), # 注意：这里可能需要调整以避免过拟合或尺寸问题 layers.Flatten(), layers.Dense(84, activation='relu'), layers.Dense(10, activation='softmax') ]) 

编译模型 

model.compile(optimizer=optimizers.Adam(), loss='categorical_crossentropy', metrics=['accuracy']) 

训练模型 

model.fit(train_images, train_labels, epochs=10, batch_size=64, validation_data=(test_images, test_labels))

评估模型

test_loss, test_acc = model.evaluate(test_images, test_labels) print(f'Test Accuracy: {test_acc:.4f}')

训练模型保存

save_path = r'D:\\图像处理、深度学习\\训练保存\\LeNet-5.h5'model.save(save_path)

这篇关于LeNet-5训练神经网络训练的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！

---