tensorflow2.0复现vgg16

最新推荐文章于 2021-10-01 18:53:35 发布

过去的时候

最新推荐文章于 2021-10-01 18:53:35 发布

阅读量1.7k

点赞数 1

CC 4.0 BY-SA版权

本文链接：https://blog.youkuaiyun.com/weixin_43886213/article/details/98972561

本文介绍了如何在TensorFlow 2.0环境下复现经典的VGG16深度学习模型，提供了权重文件的下载链接。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

tensorflow2.0复现见这里
权重文件这里下载

from tensorflow import keras
import skimage
import numpy as np
import tensorflow as tf
from PIL import Image
VGG_MEAN = [103.939, 116.779, 123.68]


# define input layer
input_layer = tf.keras.layers.Input([224, 224, 3])

red, green, blue = tf.split(axis=3, num_or_size_splits=3, value=input_layer)
bgr = tf.concat(axis=3, values=[blue - VGG_MEAN[0], green - VGG_MEAN[1], red - VGG_MEAN[2]])

# Block 1
conv1_1 = tf.keras.layers.Conv2D(filters=64, kernel_size=[3, 3], strides=[1, 1], padding='same',
                                 use_bias=True, activation='relu', name='conv1_1')(bgr)

conv1_2 = tf.keras.layers.Conv2D(filters=64, kernel_size=[3, 3], strides=[1, 1], padding='same',
                                 use_bias=True, activation='relu', name='conv1_2')(conv1_1)
pool1_1 =