多层感知机进行手写数字识别训练与预测：

# -*- coding: UTF-8 -*-
import numpy as np
from keras.datasets import mnist
from keras.layers import Dense
from keras.models import Sequential, load_model

# 加载数据
local_path = '/home/data/keras/mnist.npz'
(x_train, y_train), (x_test, y_test) = mnist.load_data(path=local_path);
print(x_train.shape, y_train.shape, x_test.shape, y_test.shape)
# (60000, 28, 28) (60000,) (10000, 28, 28) (10000,)

# 将二维的图片矩阵转换成一维数组，每个像素数值除以255归一化到0-1的数值
dim = x_train.shape[1] * x_train.shape[2]
x_train = x_train.reshape((x_train.shape[0], dim)) / 255
x_test = x_test.reshape((x_test.shape[0], dim)) / 255
print(x_train.shape, x_test.shape)
# (60000, 784) (10000, 784)

# one-hot 编码
y_train_new = np.zeros((y_train.shape[0], 10))
for i, num in enumerate(y_train):
    y_train_new[i][num] = 1

y_test_new = np.zeros((y_test.shape[0], 10))
for i, num in enumerate(y_test):
    y_test_new[i][num] = 1


def train():
    # 构造多层感知机模型
    model = Sequential()
    model.add(Dense(256, input_dim=dim, activation='relu'))
    model.add(Dense(10, activation='softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    print(model.summary())
    # Model: "sequential_1"
    # _________________________________________________________________
    # Layer (type)                 Output Shape              Param #
    # =================================================================
    # dense_1 (Dense)              (None, 256)               200960
    # _________________________________________________________________
    # dense_2 (Dense)              (None, 10)                2570
    # =================================================================
    # Total params: 203,530
    # Trainable params: 203,530
    # Non-trainable params: 0
    # _________________________________________________________________
    # None

    # 训练模型
    model.fit(x_train, y_train_new, epochs=10, batch_size=50)

    # 模型评估
    score = model.evaluate(x_test, y_test_new)
    print(score)
    # [0.07887125950443005, 0.9782999753952026]

    model.save("../data/mnist.h5")


def predict():
    model = load_model("../data/mnist.h5")
    y = model.predict(x_test[:5])
    print("predict=>", np.argmax(y, axis=1))
    print("real=>", y_test[:5])
    # predict = > [7 2 1 0 4]
    # real = > [7 2 1 0 4]


train()
predict()

一个创业中的苦逼程序员