machine learning-mnist

ml8-3全连接神经网络实现mnist手写识别

import numpy as np
from keras.models import _clone_sequential_model
from keras.models import Sequential
from keras.layers.core import Dense,Dropout,Activation
from keras.layers import Conv2D,MaxPooling2D,Flatten
from keras.optimizers import SGD,Adam
from keras.datasets import mnist
from keras.utils import np_utils
import keras
import matplotlib.pyplot as plt
import tensorflow as tf
import os

def load_data():
    (x_train,y_train),(x_test,y_test)=mnist.load_data()
    number=10000
    x_train=x_train[0:number]
    y_train=y_train[0:number]
    x_train=x_train.reshape(number,28*28)
    x_test=x_test.reshape(x_test.shape[0],28*28)
    #转化为float类型
    x_train=x_train.astype('float32')
    x_test=x_test.astype('float32')

    y_train=np_utils.to_categorical(y_train,10)
    y_test = np_utils.to_categorical(y_test, 10)
    x_train=x_train
    x_test=x_test
    #nomal归一化
    x_train=x_train/255
    x_test=x_test/255
#    x_test=np.random.normal(x_test)#加入噪声
    return(x_train,y_train),(x_test,y_test)

(x_train,y_train),(x_test,y_test)=load_data()
#定义模型
model=Sequential()
model.add(Dense(input_dim=28*28,units=689,activation='relu'))
#model.add(Dropout(0.7))
model.add(Dense(units=689,activation='relu'))
#model.add(Dropout(0.7))
model.add(Dense(units=689,activation='relu'))
#model.add(Dropout(0.7))
# for i in range(10):
#     model.add(Dense(units=689,activation='relu'))
model.add(Dense(units=10,activation='softmax'))
model.compile(loss='categorical_crossentropy',optimizer=SGD(lr=0.1),metrics=['accuracy'])
#model.compile(loss='categorical_crossentropy',optimizer=Adam(lr=0.1),metrics=['accuracy'])
#训练
model.fit(x_train,y_train,batch_size=100,epochs=20)
model.save('mymodel1')
#评估
result=model.evaluate(x_train,y_train,batch_size=10000)
print('train acc',result[1])
result=model.evaluate(x_test,y_test,batch_size=10000)
print('test acc',result[1])
#保存测试
new_model = keras.models.load_model('mymodel1')
#new_model.compile(optimizer=tf.train.AdamOptimizer(),
                # loss='categorical_crossentropy',
                # metrics=['accuracy'])
new_model.summary()
#mypath = 'F:\\PyPractice\\ML\\testdir'

手写识别预测

import random
import numpy as np
import matplotlib.pyplot as plt
from keras.datasets import mnist
from keras.models import load_model
from PIL import Image

# # 数据集
# (_, _), (X_test, y_test) = mnist.load_data()  # 划分MNIST训练集、测试集
#
# # 随机数
# index = random.randint(0, X_test.shape[0])
# x = X_test[index]
# y = y_test[index]
x=Image.open('3.PNG')
y=3
# 显示该数字
plt.imshow(x, cmap='gray_r')
plt.title("original {}".format(y))
plt.show()

# 加载
mymodel = load_model('mymodel1')

# 预测
x.reshape = (1,784)#变成[[]]
x = x.astype('float32')
x = x/255
# x = x.flatten()[None]  # 也可以用这个
predict = mymodel.predict(x)
predict = np.argmax(predict)#取最大值的位置

#print('index:', index)
print('original:', y)
print('predicted:', predict)

猜你喜欢