Wu Yuxiong - born naturally TensorFlow senior package: Keras-CNN

# 1. Data Preprocessing

import hard

from keras import backend as K
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Flatten, Conv2D, MaxPooling2D

num_classes = 10
img_rows, img_cols = 28, 28
 
# By Keras MNIST encapsulated API loading data. Which is a trainX 60,000 * 28 * 28 array, 
# trainY is the number that corresponds to each picture. 
(trainX, trainY), (testX, testy) = mnist.load_data ()

# Set the format of the input layer according to the format requirements of the encoded image. 
IF K.image_data_format () == ' channels_first ' :
    trainX = trainX.reshape(trainX.shape[0], 1, img_rows, img_cols)
    testX = testX.reshape(testX.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    trainX = trainX.reshape(trainX.shape[0], img_rows, img_cols, 1)
    testX = testX.reshape(testX.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)
    
trainX = trainX.astype('float32')
testX = testX.astype('float32')
trainX /= 255.0 
testX /= 255.0
 
# The standard answer into a format (one-hot encoding) needs. 
= trainY keras.utils.to_categorical (trainY, num_classes)
testY = keras.utils.to_categorical(testY, num_classes)

# 2. Keras API definitions winder neural network. 
# Use Keras API defined model. 
= Model the Sequential ()
model.add(Conv2D(32, kernel_size=(5, 5), activation='relu', input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(500, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))
 
# Define the loss function, function optimization and evaluation methods. 
model.compile (Loss = keras.losses.categorical_crossentropy, keras.optimizers.SGD Optimizer = (), metrics = [ ' Accuracy ' ])

# 3 by API Keras training model and calculating accuracy on the test data. 
model.fit (trainX, trainY, the batch_size = 128, 10 = epochs, validation_data = (testX, testy))
 
# Calculation accuracy on the test data. 
= Score model.evaluate (testX, testy)
 Print ( ' the Test Loss: ' , Score [0])
 Print ( ' the Test Accuracy: ' , Score [. 1])