机器学习笔记 - tensorflow 2.8版本不同优化器对比

1、目标概述

        这里使用tensorflow 2.8版本和LeNet-5模型在mnist手写数字数据集上进行各种优化器的效率比较。为了展示现代优化器（在 TensorFlow 和 Keras 中的优化器）对训练的影响，我们将创建几个 LeNet 实例，并使用不同的优化器训练每个实例。

2、导入包准备数据

import tensorflow as tf
import numpy as np
import matplotlib
from matplotlib import pyplot as plt

num_classes = 10
img_rows, img_cols, img_ch = 28, 28, 1
input_shape = (img_rows, img_cols, img_ch)

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

x_train = x_train.reshape(x_train.shape[0], *input_shape)
x_test = x_test.reshape(x_test.shape[0], *input_shape)

print('Training data: {}'.format(x_train.shape))
print('Testing data: {}'.format(x_test.shape))

3、创建LeNet-5模型

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D

def lenet(name&