tensorflow学习笔记一——模拟一条直线方程

Session

Session在tensorflow中就像指针一样，指向需要运行的代码。Session运行结束后，需要关闭，可以利用with来自动完成。

from __future__ import print_functionimport tensorflow as tfmatrix1 = tf.constant([[3, 3]])matrix2 = tf.constant([[2],                       [2]])product = tf.matmul(matrix1, matrix2)  # matrix multiply np.dot(m1, m2)# method 1sess = tf.Session()result = sess.run(product)print(result)sess.close()# method 2with tf.Session() as sess:    result2 = sess.run(product)    print(result2)

变量

在tensorflow中，变量通过Variable函数来定义。并且一定要运行initialize_all_variables()来初始化所有变量。

from __future__ import print_functionimport tensorflow as tfstate = tf.Variable(0, name='counter')#print(state.name)one = tf.constant(1)new_value = tf.add(state, one)update = tf.assign(state, new_value)#该操作是将new_value的值赋给state.不可以用state = new_value代替init = tf.initialize_all_variables()  # must have if define variablewith tf.Session() as sess:    sess.run(init)    for _ in range(3):        sess.run(update)        print(sess.run(state))

占位符

在tensorflow中，有一部分的变量是在输入的时候才能确定的，所以可以使用占位符来先定义对这类数据的操作。

from __future__ import print_functionimport tensorflow as tfinput1 = tf.placeholder(tf.float32)input2 = tf.placeholder(tf.float32)ouput = tf.mul(input1, input2)with tf.Session() as sess:    print(sess.run(ouput, feed_dict={input1: [7.], input2: [2.]}))

模拟直线

本次利用神经网络学习来趋近一条直线方程y = 0.1x + 0.3.代码如下：

from __future__ import print_functionimport tensorflow as tfimport numpy as np# create datax_data = np.random.rand(100).astype(np.float32)y_data = x_data*0.1 + 0.3### create tensorflow structure start ###Weights = tf.Variable(tf.random_uniform([1], -1.0, 1.0))biases = tf.Variable(tf.zeros([1]))y = Weights*x_data + biases loss = tf.reduce_mean(tf.square(y-y_data))optimizer = tf.train.GradientDescentOptimizer(0.5)train = optimizer.minimize(loss)init = tf.initialize_all_variables()### create tensorflow structure end ###sess = tf.Session()sess.run(init)          # Very importantfor step in range(201):    sess.run(train)    if step % 20 == 0:        print(step, sess.run(Weights), sess.run(biases))

• tf.random_uniform(shape, minval=0, maxval=None, dtype=tf.float32, seed=None, name=None)用这个函数初始化W，得到一个一维的，取值范围在-1到1的数组，本例中就是一个数字。初始化biase为0。

• y为预测的值，y_data是正确的值，通过计算两者的差值的平方作为误差，然后用梯度下降使得误差最小。