TensorFlow是目前非常流行的deep learning框架,学习TensorFlow最好的方法是github上的tf项目https://github.com/tensorflow/tensorflow或者阅读极客学院主导翻译的中文教程http://wiki.jikexueyuan.com/project/tensorflow-zh/how_tos/reading_data.html 。
此处对tensorflow的基本语法不予赘述,直接贴上源码:
import numpy as np
import tensorflow as tf
#准备数据
trainX = np.linspace(-1, 1, 101)
trainY = 2 * trainX + np.random.randn(*trainX.shape) * 0.33
#定义模型
def model(X, w):
return tf.multiply(X, w)
#初始化数据流图
X = tf.placeholder('float')
Y = tf.placeholder('float')
w = tf.Variable(0.0, name = 'weights')
y_ = model(X, w)
#评估模型
cost = tf.square(Y - y_)
train_op = tf.train.GradientDescentOptimizer(0.01).minimize(cost)
sess = tf.InteractiveSession()
init = tf.initialize_all_variables()
#训练
sess.run(init)
for i in range(100):
for (x, y) in zip(trainX, trainY):
sess.run(train_op, feed_dict = {X: x, Y: y})
print(sess.run(w))
sess.close()