2.mnist程序运行

几种可以跑出来的代码：

---

1.MPL

from keras.models import Sequential
from keras.utils import np_utils
from keras.layers.core import Dense, Activation, Dropout

import pandas as pd
import numpy as np

# Read data
train = pd.read_csv('train.csv')
labels = train.ix[:,0].values.astype('int32')
X_train = (train.ix[:,1:].values).astype('float32')
X_test = (pd.read_csv('test.csv').values).astype('float32')

# convert list of labels to binary class matrix
y_train = np_utils.to_categorical(labels) 

# pre-processing: divide by max and substract mean
scale = np.max(X_train)
X_train /= scale
X_test /= scale

mean = np.std(X_train)
X_train -= mean
X_test -= mean

input_dim = X_train.shape[1]
nb_classes = y_train.shape[1]

# Here's a Deep Dumb MLP (DDMLP)
model = Sequential()
model.add(Dense(128, input_dim=input_dim))
model.add(Activation('relu'))
model.add(Dropout(0.15))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.15))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

# we'll use categorical xent for the loss, and RMSprop as the optimizer
model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

print("Training...")
model.fit(X_train, y_train, nb_epoch=10, batch_size=16, validation_split=0.1,verbose=2)


print("Generating test predictions...")
preds = model.predict_classes(X_test, verbose=0)

def write_preds(preds, fname):
    pd.DataFrame({"ImageId": list(range(1,len(preds)+1)), "Label": preds}).to_csv(fname, index=False, header=True)

write_preds(preds, "keras-mlp.csv")

2.cnn

只是个小的例子，把参数，层数设的很小，仅供参考。
跑出来还是很开心滴~~~

---

代码部分：存成.py

获取数据部分

# %load data.py
"""
Author:wepon
Source:https://github.com/wepe

"""
import os
from PIL import Image
import numpy as np
from collections import Counter

#读取文件夹mnist下的42000张图片，图片为灰度图，所以为1通道，图像大小28*28
#如果是将彩色图作为输入,则将1替换为3，并且data[i,:,:,:] = arr
改为data[i,:,:,:] = [arr[:,:,0],arr[:,:,1],arr[:,:,2]]

def load_data():
    data = np.empty((42000,1,28,28),dtype="float32")
    label = np.empty((42000,),dtype="uint8")

    imgs = os.listdir("./mnist")
    num = len(imgs)
    for i in range(num):    
        img = Image.open("./mnist/"+imgs[i])
        arr = np.asarray(img,dtype="float32")
        data[i,:,:,:] = arr 
        label[i] = int(imgs[i].split('.')[0])
    cnt = Counter(label)
    for k,v in cnt.iteritems():
        print (k, '-->', v)
    return data,label

搭建cnn网络
保存成cnn.py

# %load cnn.py

'''
    GPU run command:
        THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python cnn.py
    CPU run command:
        python cnn.py
'''
#导入各种用到的模块组件
from __future__ import absolute_import
from __future__ import print_function
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.advanced_activations import PReLU
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD, Adadelta, Adagrad
from keras.utils import np_utils, generic_utils
from six.moves import range
from data import load_data
from keras.callbacks import EarlyStopping
import random
from collections import Counter


#加载数据
data, label = load_data()
#打乱数据
index = [i for i in range(len(data))]
random.shuffle(index)
data = data[index]
label = label[index]
print(data.shape[0], ' samples')

#label为0~9共10个类别，keras要求格式为binary class matrices,转化一下，直接调用keras提供的这个函数
label = np_utils.to_categorical(label, 10)

###############
#开始建立CNN模型
###############

#生成一个model
model = Sequential()

#第一个卷积层，4个卷积核，每个卷积核大小5*5。1表示输入的图片的通道,灰度图为1通道。
#border_mode可以是valid或者full，具体看这里说明：http://deeplearning.net/software/theano/library/tensor/nnet/conv.html#theano.tensor.nnet.conv.conv2d
#激活函数用tanh
#你还可以在model.add(Activation('tanh'))后加上dropout的技巧: model.add(Dropout(0.5))
model.add(Convolution2D(4, 5, 5, border_mode='valid',input_shape=data.shape[-3:])) 
model.add(Activation('tanh'))

#第二个卷积层，8个卷积核，每个卷积核大小3*3。4表示输入的特征图个数，等于上一层的卷积核个数
#激活函数用tanh
#采用maxpooling，poolsize为(2,2)
model.add(Convolution2D(8, 3, 3, border_mode='valid'))
model.add(Activation('tanh'))
model.add(MaxPooling2D(pool_size=(2, 2)))

#第三个卷积层，16个卷积核，每个卷积核大小3*3
#激活函数用tanh
#采用maxpooling，poolsize为(2,2)
model.add(Convolution2D(16, 3, 3, border_mode='valid')) 
model.add(Activation('tanh'))
model.add(MaxPooling2D(pool_size=(2, 2)))

#全连接层，先将前一层输出的二维特征图flatten为一维的。
#Dense就是隐藏层。16就是上一层输出的特征图个数。4是根据每个卷积层计算出来的：(28-5+1)得到24,(24-3+1)/2得到11，(11-3+1)/2得到4
#全连接有128个神经元节点,初始化方式为normal
model.add(Flatten())
model.add(Dense(128, init='normal'))
model.add(Activation('tanh'))


#Softmax分类，输出是10类别
model.add(Dense(10, init='normal'))
model.add(Activation('softmax'))


#############
#开始训练模型
##############
#使用SGD + momentum
#model.compile里的参数loss就是损失函数(目标函数)
sgd = SGD(lr=0.05, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd,class_mode="categorical",metrics=["accuracy"])

#调用fit方法，就是一个训练过程. 训练的epoch数设为10，batch_size为100．
#数据经过随机打乱shuffle=True。verbose=1，训练过程中输出的信息，0、1、2三种方式都可以，无关紧要。show_accuracy=True，训练时每一个epoch都输出accuracy。
#validation_split=0.2，将20%的数据作为验证集。

early_stopping = EarlyStopping(monitor='val_loss', patience=2)
#在fit中用回调函数，val_loss不在减小时候自动停止

hist = model.fit(data, label, batch_size=100, nb_epoch=10,shuffle=True,verbose=1,validation_split=0.2, callbacks=[early_stopping])
print(hist.history)

pre_temp=model.predict_classes(data)
cnt = Counter(pre_temp)
for k,v in cnt.iteritems():
    print (k, '-->', v)

json_string = model.to_json()
open('my_model.json','w').write(json_string)
model.save_weights('mnist_cnn_model.h5')

---

运行全过程

1.路径调到文件夹下：

import os
os.chdir('C:/Users/ZWT/Desktop/1/cnn_minst_keras/')
# 到文件夹下面

2.运行cnn.py

run cnn.py

3.保存模型

#from keras.models import load_model
import h5py
model.save('my.h5')

4.运行保存好的模型

from keras.models import load_model

model=load_model('my.h5') #加载模型
print "test my load:"
print model.predict_classes(X_test)

5.也可以用另一种方式保存模型

保存权重

json_string = model.to_json()
open('my_model.json','w').write(json_string)
model.save_weights('mnist_cnn_model.h5')

调用

from keras.models import load_model,model_from_json
model=model_from_json(open('my_model.json').read())
model.load_weights('mnist_cnn_model.h5')

---