vgg16模型tensorflow2.64实现

最新推荐文章于 2023-03-10 21:19:16 发布

「已注销」

最新推荐文章于 2023-03-10 21:19:16 发布

阅读量329

点赞数 1

分类专栏：深度学习文章标签： tensorflow 深度学习 python

本文链接：https://blog.csdn.net/m0_73817310/article/details/127010253

版权

该博客详细介绍了如何在TensorFlow 2.64版本中实现VGG16深度学习模型，包括多个卷积层、激活函数、池化层以及全连接层的构建，总计参数数量为14,734,149。" 106767350,7482256,自定义parent项目下如何使用springboot的依赖管理,"['Java', 'Spring Boot', '依赖管理', '项目构建']

摘要由CSDN通过智能技术生成

from tensorflow.keras import layers
from tensorflow import keras

data_augmentation = keras.Sequential(
    [layers.RandomFlip("horizontal"), 
     layers.RandomRotation(0.1),]
)

inputs = keras.Input(shape=(180, 180, 3))
x = data_augmentation(inputs)
x = layers.Rescaling(1./255)(x)

x = layers.Conv2D(filters=64,kernel_size=3, padding='same')(x)
x = layers.Activation('relu')(x)
x = layers.BatchNormalization()(x)
x = layers.Conv2D(filters=64,kernel_size=3, padding='same')(x)
x = layers.Activation('relu')(x)
x = layers.BatchNormalization()(x)
x = layers.MaxPool2D((2,2))(x)

x = layers.Conv2D(filters=128,kernel_size=3, padding='same')(x)
x = layers.Activation('relu')(x)
x = layers.BatchNormalization()(x)
x = layers.Conv2D(filters=128,kernel_size=3, padding='same')(x)
x = layers.Activation('relu')(x)
x = layers.BatchNormalization()(x)
x = layers.MaxPool2D((2,2))(x)

x = layers.Conv2D(filters=256,kernel_size=3, padding='same')(x)
x = layers.Activation('relu')(x)
x = layers.BatchNormalization()(x)
x = layers.Conv2D(filters=256,kernel_size=3, padding='same')(x)
x = layers.Activation('relu')(x)
x = layers.BatchNormalization()(x)
x = layers.Conv2D(filters=256,kernel_size=3, padding='same')(x)
x = layers.Activation('relu')(x)
x = layers.BatchNormalization()(x)
x = layers.MaxPool2D((2,2))(x)


x = layers.Conv2D(filters=512,kernel_size=3, padding='same')(x)
x = layers.Activation('relu')(x)
x = layers.BatchNormalization()(x)
x = layers.Conv2D(filters=512,kernel_size=3, padding='same')(x)
x = layers.Activation('relu')(x)
x = layers.BatchNormalization()(x)
x = layers.Conv2D