目录
效果展示
基础理论
1、softmax激活函数
2、神经网络
3、隐藏层及神经元最佳数量
一、数据准备
1、载入数据集
2、数据处理
2-1、归一化
2-2、独热编码
二、神经网络拟合
1、搭建神经网络
2、设置优化器、损失函数
3、训练
三、预测
1、备份图像数据集
2、预测分类
3、显示结果(plt)
总代码
这里输出层用到了softmax激活函数,把输出的数据转化成概率:
神经网络原型:
28*28=784个输入像素对应784个输入神经元;10个输出神经元分别对应0~9的十个数。
(为了提高训练的准确度,我加了一些隐藏层 )
隐藏层、神经元最佳数量需要自己不断实验获得,先选取小一点的数据,欠拟合,再不断增加数据,直到最佳数据出现(即将出现过拟合情况)。
通常:
# 数据准备
def Data_Preparation():
global train_data, train_label, test_data, test_label, mnist_train, \
mnist_test, images, labels
# 1、载入数据集
mnist = tf.keras.datasets.mnist
(train_data, train_label), (test_data, test_label) = mnist.load_data()
# 训练集数据 train_data 的数据形状为(60000,28,28)
# 训练集标签 train_label 的数据形状为(60000)
# 测试集数据 test_data 的数据形状为(10000,28,28)
# 测试集标签 test_label 的数据形状为(10000)
images, labels = test_data, test_label
# 2-1、数据集归一化
train_data = train_data/255
test_data = test_data/255
0~9分别用10个二进制数中1的位置表示它们的值。
# 2-2、标签独热编码
train_label = tf.keras.utils.to_categorical(train_label, num_classes=10)
test_label = tf.keras.utils.to_categorical(test_label, num_classes=10)
# 转化为独热编码 待转数据 独热码长度
输入层(数据展平:(28,28)->(784))、隐藏层、输出层(10个神经元对应10个数字)。
# 1、创建神经网络
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)), # 输入数据压缩,三维变二维
# (60000,28,28) -> (60000, 784)
tf.keras.layers.Dense(200 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(200 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(200 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(100 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(100 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(100 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(10, activation='softmax') # 全连接层
# 输出神经元数量 激活函数(softmax)
])
隐藏层数和神经元数量非固定的,自己测试之后添加的。
添加隐层前:
添加隐层后;
# 2、设置优化器、损失函数
model.compile(optimizer=SGD(0.3), loss='mse', metrics=['accuracy'])
# 优化器 学习率0.3 损失函数(均方误差) 保留标签(accuracy)
目前测试的最佳学习率:0.3(本模型)
# 3、训练
model.fit(train_data, train_label, epochs=20, batch_size=32, validation_data=(test_data, test_label))
# 训练集 遍历20次 一组32个 测试集
这里准备了2个图像数据集,一份用于后面的预测分类,一份用于显示图像。
为什么不用一份呢?因为两者维度不同,预测的需要更高一维度的数据。
# 图像增加维度
Images = images[:, np.newaxis]
# images图像正常显示,Images图像用来做预测
# 预测分类
classification = model.predict(Images[i], batch_size=10)
# 得到结果
result.append(np.argmax(classification[0]))
# 显示结果
x = int(i/3)
y = i%3
ax[x][y].set_title(f'label:{labels[i]}-predict:{result[i]}') # 设置标题
ax[x][y].imshow(images[i], 'gray') # 显示图像
ax[x][y].axis('off') # 隐藏坐标轴
训练1次:
训练30次:
训练了30次的情况:
D:\Software\Python\Python\python.exe D:/Study/AI/OpenCV/draft.py/main.py
Epoch 1/30
1875/1875 [==============================] - 6s 3ms/step - loss: 0.0393 - accuracy: 0.7064 - val_loss: 0.0114 - val_accuracy: 0.9270
Epoch 2/30
1875/1875 [==============================] - 5s 3ms/step - loss: 0.0105 - accuracy: 0.9310 - val_loss: 0.0075 - val_accuracy: 0.9498
Epoch 3/30
1875/1875 [==============================] - 5s 3ms/step - loss: 0.0072 - accuracy: 0.9538 - val_loss: 0.0062 - val_accuracy: 0.9603
Epoch 4/30
1875/1875 [==============================] - 5s 3ms/step - loss: 0.0057 - accuracy: 0.9635 - val_loss: 0.0055 - val_accuracy: 0.9658
Epoch 5/30
1875/1875 [==============================] - 5s 3ms/step - loss: 0.0047 - accuracy: 0.9703 - val_loss: 0.0048 - val_accuracy: 0.9691
Epoch 6/30
1875/1875 [==============================] - 5s 3ms/step - loss: 0.0040 - accuracy: 0.9746 - val_loss: 0.0048 - val_accuracy: 0.9694
Epoch 7/30
1875/1875 [==============================] - 6s 3ms/step - loss: 0.0034 - accuracy: 0.9787 - val_loss: 0.0049 - val_accuracy: 0.9669
Epoch 8/30
1875/1875 [==============================] - 5s 3ms/step - loss: 0.0030 - accuracy: 0.9816 - val_loss: 0.0043 - val_accuracy: 0.9713
Epoch 9/30
1875/1875 [==============================] - 6s 3ms/step - loss: 0.0026 - accuracy: 0.9844 - val_loss: 0.0038 - val_accuracy: 0.9760
Epoch 10/30
1875/1875 [==============================] - 6s 3ms/step - loss: 0.0023 - accuracy: 0.9864 - val_loss: 0.0050 - val_accuracy: 0.9677
Epoch 11/30
1875/1875 [==============================] - 7s 4ms/step - loss: 0.0021 - accuracy: 0.9873 - val_loss: 0.0037 - val_accuracy: 0.9764
Epoch 12/30
1875/1875 [==============================] - 6s 3ms/step - loss: 0.0018 - accuracy: 0.9894 - val_loss: 0.0037 - val_accuracy: 0.9758
Epoch 13/30
1875/1875 [==============================] - 7s 4ms/step - loss: 0.0017 - accuracy: 0.9901 - val_loss: 0.0041 - val_accuracy: 0.9734
Epoch 14/30
1875/1875 [==============================] - 7s 4ms/step - loss: 0.0015 - accuracy: 0.9911 - val_loss: 0.0045 - val_accuracy: 0.9708
Epoch 15/30
1875/1875 [==============================] - 7s 4ms/step - loss: 0.0014 - accuracy: 0.9921 - val_loss: 0.0038 - val_accuracy: 0.9760
Epoch 16/30
1875/1875 [==============================] - 7s 4ms/step - loss: 0.0013 - accuracy: 0.9922 - val_loss: 0.0036 - val_accuracy: 0.9764
Epoch 17/30
1875/1875 [==============================] - 6s 3ms/step - loss: 0.0012 - accuracy: 0.9932 - val_loss: 0.0035 - val_accuracy: 0.9771
Epoch 18/30
1875/1875 [==============================] - 6s 3ms/step - loss: 0.0011 - accuracy: 0.9942 - val_loss: 0.0034 - val_accuracy: 0.9783
Epoch 19/30
1875/1875 [==============================] - 7s 4ms/step - loss: 9.5588e-04 - accuracy: 0.9947 - val_loss: 0.0034 - val_accuracy: 0.9788
Epoch 20/30
1875/1875 [==============================] - 6s 3ms/step - loss: 9.9405e-04 - accuracy: 0.9942 - val_loss: 0.0037 - val_accuracy: 0.9767
Epoch 21/30
1875/1875 [==============================] - 7s 4ms/step - loss: 8.7466e-04 - accuracy: 0.9952 - val_loss: 0.0037 - val_accuracy: 0.9757
Epoch 22/30
1875/1875 [==============================] - 7s 4ms/step - loss: 7.5603e-04 - accuracy: 0.9959 - val_loss: 0.0037 - val_accuracy: 0.9773
Epoch 23/30
1875/1875 [==============================] - 7s 4ms/step - loss: 7.8775e-04 - accuracy: 0.9955 - val_loss: 0.0035 - val_accuracy: 0.9783
Epoch 24/30
1875/1875 [==============================] - 7s 4ms/step - loss: 7.2748e-04 - accuracy: 0.9961 - val_loss: 0.0034 - val_accuracy: 0.9779
Epoch 25/30
1875/1875 [==============================] - 7s 4ms/step - loss: 7.2780e-04 - accuracy: 0.9959 - val_loss: 0.0036 - val_accuracy: 0.9777
Epoch 26/30
1875/1875 [==============================] - 6s 3ms/step - loss: 5.9373e-04 - accuracy: 0.9969 - val_loss: 0.0032 - val_accuracy: 0.9792
Epoch 27/30
1875/1875 [==============================] - 6s 3ms/step - loss: 5.6153e-04 - accuracy: 0.9970 - val_loss: 0.0034 - val_accuracy: 0.9786
Epoch 28/30
1875/1875 [==============================] - 7s 4ms/step - loss: 5.7011e-04 - accuracy: 0.9969 - val_loss: 0.0033 - val_accuracy: 0.9792
Epoch 29/30
1875/1875 [==============================] - 7s 4ms/step - loss: 5.0371e-04 - accuracy: 0.9973 - val_loss: 0.0037 - val_accuracy: 0.9767
Epoch 30/30
1875/1875 [==============================] - 7s 4ms/step - loss: 5.2224e-04 - accuracy: 0.9972 - val_loss: 0.0033 - val_accuracy: 0.9795
可以发现,训练次数过高,后面变化就已经不大了。
# keras手写数字识别
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
import tensorflow as tf
from tensorflow.keras.optimizers import SGD
import numpy as np
import matplotlib.pyplot as plt
# 数据准备
def Data_Preparation():
global train_data, train_label, test_data, test_label, mnist_train, \
mnist_test, images, labels
# 1、载入数据集
mnist = tf.keras.datasets.mnist
(train_data, train_label), (test_data, test_label) = mnist.load_data()
# 训练集数据 train_data 的数据形状为(60000,28,28)
# 训练集标签 train_label 的数据形状为(60000)
# 测试集数据 test_data 的数据形状为(10000,28,28)
# 测试集标签 test_label 的数据形状为(10000)
images, labels = test_data, test_label
# 2、数据处理(归一化、独热编码)
# 2-1、数据集归一化
train_data = train_data/255
test_data = test_data/255
# 2-2、标签独热编码
train_label = tf.keras.utils.to_categorical(train_label, num_classes=10)
test_label = tf.keras.utils.to_categorical(test_label, num_classes=10)
# 转化为独热编码 待转数据 独热码长度
# 神经网络拟合
def Neural_Network():
global model
# 1、创建神经网络
model = tf.keras.models.Sequential([
#
tf.keras.layers.Flatten(input_shape=(28, 28)), # 输入数据压缩,三维变二维
# (60000,28,28) -> (60000, 784)
tf.keras.layers.Dense(200 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(200 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(200 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(100 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(100 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(100 + 1, activation=tf.nn.relu),
tf.keras.layers.Dense(10, activation='softmax') # 全连接层
# 输出神经元数量 激活函数(softmax)
])
# 2、设置优化器、损失函数
model.compile(optimizer=SGD(0.3), loss='mse', metrics=['accuracy'])
# 优化器 学习率0.3 损失函数(均方误差) 保留标签(accuracy)
# 3、训练
model.fit(train_data, train_label, epochs=20, batch_size=32, validation_data=(test_data, test_label))
# 训练集 遍历20次 一组32个 测试集
# 预测手写数字(可视化部分测试集的预测)
def Predict():
global images
# 预测结果
result = []
# plt图表
f, ax = plt.subplots(3, 3, figsize=(8, 6))
# 图像增加维度
Images = images[:, np.newaxis]
# images图像正常显示,Images图像用来做预测
# 在测试集中选取一部分数据进行可视化分类
for i in range(9):
# 预测分类
classification = model.predict(Images[i], batch_size=10)
# 得到结果
result.append(np.argmax(classification[0]))
# 显示结果
x = int(i/3)
y = i%3
ax[x][y].set_title(f'label:{labels[i]}-predict:{result[i]}') # 设置标题
ax[x][y].imshow(images[i], 'gray') # 显示图像
ax[x][y].axis('off') # 隐藏坐标轴
plt.show()
# 数据准备
Data_Preparation()
# 神经网络搭建
Neural_Network()
# 手写数字预测
Predict()