数据集介绍:
Keras里已经封装好了mnist数据集(包含6000张训练数据,1000张测试数据),图片大小为28x28。一行代码就可以从keras里导入进来,第一次导入时间长点,请慢慢等待。
from keras.datasets import mnist
导入各种包
from keras.layers import Dense, Dropout, Convolution2D
from keras.layers import MaxPooling2D
from keras import Sequential
from keras.datasets import mnist
from keras.optimizers import Adam
from keras.utils import np_utils
from keras.layers import Flatten
import matplotlib.pyplot as plt
数据归一化
(X_train, Y_train), (X_test, Y_test) = mnist.load_data()
X_train = X_train.reshape(-1, 28, 28, 1)/255.0
X_test = X_test.reshape(-1, 28, 28, 1)/255.0
Y_train = np_utils.to_categorical(Y_train, num_classes=10)
Y_test = np_utils.to_categorical(Y_test, num_classes=10)
使用keras搭建网络模型
手写字属于10分类,最后一层全连接层和分类数相匹配,两层全连接层中间加Dropout层,按比例丢弃神经元,抑制过拟合。
model = Sequential()
model.add(Convolution2D(12, kernel_size=5, activation='relu', strides=1,
padding='same', input_shape=(28, 28, 1)))
model.add(MaxPooling2D(pool_size=2, strides=2, padding