Deep learning ----- different methods to realize vgg16

This blog is through tensorflow Realization vgg-16 Model , about vgg-16 There are different ways to write models , Include ,sequence Model 、 Class encapsulation 、 Custom function , This blog mainly introduces these three writing methods , The code and diagram are as follows ：

The size of this picture is 224x224x3 Picture size of the channel , This code is slightly modified , use 32x32x3 Take the picture of the channel as an example , It is trained under the condition that the convolution kernel and the number of channels are constant vgg-16 Model .

1. tensofflow adopt sequence Realization vgg-16

from tensorflow.keras.datasets import cifar10
import tensorflow as tf
from tensorflow.keras import models,Sequential
from tensorflow.