TensorFlow (keras) 房价回归预测模型 Coursera深度学习课程分享

这个课程实在太简单，一步步构建一个最最基本的回归模型，代码如下。

import tensorflow as tf
from tensorflow import keras
from keras.models import Sequential
from keras.layers import Dense
import numpy as np
import matplotlib.pylab as plt

构建模型

model = Sequential()
model.add(Dense(1, input_shape=[1]))
model.output_shape, model.input_shape
optimizer = tf.train.AdamOptimizer(learning_rate=1e-3)
model.compile(optimizer, loss='mean_squared_error', metrics=['mse'])

构建数据

x = np.linspace(1, 20, 20)
y = x * 50  # +  np.random.randn(20) * 10
x =  x / np.max(x)
y = y / np.max(y)
print('x: {}'.format(x), '\ny: {}'.format(y))
#绘制数据
plt.scatter(x, y)

x: [0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5 0.55 0.6 0.65 0.7
0.75 0.8 0.85 0.9 0.95 1. ]
y: [0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5 0.55 0.6 0.65 0.7
0.75 0.8 0.85 0.9 0.95 1. ]

模型训练，非常简单：

model.fit(x, y, batch_size=1000, epochs=5)

Epoch 1/5
20/20 [==============================] - 0s 6ms/step - loss: 0.0129 - mean_squared_error: 0.0129
Epoch 2/5
20/20 [==============================] - 0s 170us/step - loss: 0.0125 - mean_squared_error: 0.0125
Epoch 3/5
20/20 [==============================] - 0s 135us/step - loss: 0.0122 - mean_squared_error: 0.0122