Karas MNISt数据集识别

import struct
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense,Dropout,Flatten
from keras.layers import Conv2D,MaxPooling2D
from keras import backend
import os
import numpy as np
def load_mnist(path,kind="train"):
    labels_path=os.path.join(path, '%s-labels-idx1-ubyte' % kind)
    images_path=os.path.join(path, '%s-images-idx3-ubyte' % kind)
    with open(labels_path,'rb') as lbpath:
        magic, n = struct.unpack('>II', lbpath.read(8))
        labels = np.fromfile(lbpath, dtype=np.uint8)

    with open(images_path, 'rb') as imgpath:
        magic, num, rows, cols = struct.unpack(">IIII", imgpath.read(16))
        images = np.fromfile(imgpath, dtype=np.uint8).reshape(len(labels), 784)
        #        Construct an array from data in a text or binary file.

    return images, labels

path=".\data"
X_train, y_train =load_mnist(path , kind='train')
print('Rows:%d,columns:%d' % (X_train.shape[0], X_train.shape[1]))
X_test, y_test = load_mnist(path, kind='t10k')
print('Rows:%d,columns:%d' % (X_test.shape[0], X_test.shape[1]))




print(type(X_train)) #<class 'numpy.ndarray'>
print(y_train)#[5 0 4 ... 5 6 8]
print(y_train.shape)#60000,
batch_size=128
num_classes=10
epochs=1

'''
def image_data_format():
    """Returns the default image data format convention ('channels_first' or 'channels_last').

    # Returns
        A string, either `'channels_first'` or `'channels_last'`

'''

if backend.image_data_format()=='channels_first':
    X_train=X_train.reshape(X_train.shape[0],1,28,28)
    X_test=X_test.reshape(X_test.shape[0],1,28,28)
    input_shape=(1,28,28)
else:
    X_train = X_train.reshape(X_train.shape[0], 28, 28,1)
    X_test = X_test.reshape(X_test.shape[0], 28, 28,1)
    input_shape=(28,28,1)





X_train=X_train.astype('float32')
X_test=X_test.astype('float32')
# TypeError: No loop matching the specified signature and casting
# was found for ufunc true_divide()
#防止下面两条出错
X_train /=255
X_test /=255
print('x_train shape',X_train.shape)
#(60000, 28, 28, 1)

#convert class vectors to binary class matrices
#one hot编码
import keras
y_train=keras.utils.to_categorical(y_train,num_classes)
y_test=keras.utils.to_categorical(y_test,num_classes)
print(y_train.shape) #(60000, 10)
print(y_train[0])  #[0. 0. 0. 0. 0. 1. 0. 0. 0. 0.]


model=Sequential()
#[3*3*32]
#(60000, 28, 28, 1)->(60000, 26, 26, 32)
model.add(Conv2D(32,kernel_size=(3,3),activation='relu',input_shape=input_shape,padding="valid",strides=(1,1)))
#(60000, 26, 26, 32)->(60000, 24, 24, 64)
model.add(Conv2D(64,kernel_size=(3,3),activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
#(60000, 24, 24, 64)->(60000, 12, 12, 64)
model.add(Dropout(0.25))#防止过拟合
model.add(Flatten())
#(60000, 12, 12, 64)->(60000, 12*12* 64)

"""

model = Sequential()
model.add(Conv2D(64, (3, 3),
                 input_shape=(3, 32, 32), padding='same', ))
# now: model.output_shape == (None, 64, 32, 32)

model.add(Flatten())
# now: model.output_shape == (None, 65536)
"""


model.add(Dense(units=128,activation='relu'))
    #`Dense` implements the operation:
    #`output = activation(dot(input, kernel) + bias)`
#(60000, 12*12* 64)->(60000, 128)
model.add(Dropout(0.5))
model.add(Dense(units=num_classes,activation="softmax"))
model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),metrics=['accuracy'])
print(model)

model.fit(x=X_train,y=y_train,batch_size=batch_size,epochs=epochs,verbose=1,validation_data=(X_test,y_test))
score=model.evaluate(x=X_test,y=y_test,verbose=0)
"""Returns the loss value & metrics values for the model in test mode.

       Computation is done in batches."""
print("Test Loss:",score[0])
print("Test accuracy:",score[1])


#模型保存
model.save("mnist.model")

print()