keras 简单使用

import keras
import numpy as np
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense

# 使用numpy生成100个随机点
x_data = np.random.rand(100)
noise = np.random.normal(0, 0.02, x_data.shape)
y_data = x_data*0.1 + 0.2 + noise

# 构建模型
model = Sequential()
model.add(Dense(1, input_dim=1))
model.compile(optimizer=‘sgd‘, loss=‘mse‘)

# 训练模型
for step in range(3001):
    cost = model.train_on_batch(x_data, y_data)
    if step % 500 == 0:
        print(‘cost:‘, cost)

# 打印出权值和偏置值
w, b = model.layers[0].get_weights()
print(‘W:‘, w, ‘B: ‘, b)

import keras
import numpy as np
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD

# 生成一批数据
x_data = np.linspace(-0.5, 0.5, 200)
noise = np.random.normal(0, 0.02, x_data.shape)
y_data = np.square(x_data) + noise

# 构建模型
model = Sequential()
model.add(Dense(10, input_dim=1, activation=‘tanh‘))
model.add(Dense(1))
sgd = SGD(lr=0.1)
model.compile(optimizer=sgd, loss=‘mse‘)

# 训练模型
for step in range(3001):
    cost = model.train_on_batch(x_data, y_data)
    if step % 500 == 0:
        print(‘cost:‘, cost)

# 打印出权值和偏置值
w, b = model.layers[0].get_weights()
print(‘W:‘, w, ‘B: ‘, b)

import keras
from keras.datasets import mnist
from keras.utils import  np_utils
import numpy as np
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense

# 载入数据
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# 转换数据格式
x_train = x_train.reshape(x_train.shape[0], -1)
x_test = x_test.reshape(x_test.shape[0], -1)
y_train = np_utils.to_categorical(y_train, num_classes=10)
y_test = np_utils.to_categorical(y_test, num_classes=10)

# 创建模型
model = Sequential()
model.add(Dense(64, input_dim=784, bias_initializer=‘one‘, activation=‘sigmoid‘))
model.add(Dense(10, bias_initializer=‘one‘, activation=‘softmax‘))
model.compile(optimizer=‘adam‘, loss=‘categorical_crossentropy‘, metrics=[‘acc‘])
model.fit(x_train, y_train, batch_size=128, epochs=10)

loss, accurancy = model.evaluate(x_test, y_test)
print(‘loss: ‘, loss)
print(‘accurancy: ‘, accurancy)