Tensorflow实现一个简单的二分类问题

说好的每天一更··结果只坚持了一天···笑
从头开始学习

import tensorflow as tf#这里通过numpy工具包来生成模拟数据集from numpy.random import RandomState#定义训练数据batch的大小batch_size = 8#定义神经网络参数w1 = tf.Variable(tf.random_normal([2,3],stddev = 1,seed = 1))w2 = tf.Variable(tf.random_normal([3,1],stddev = 1,seed = 1))#在训练时需要把数据分成较小的batchx = tf.placeholder(tf.float32,shape=(None,2),name = 'x-input')y_ = tf.placeholder(tf.float32,shape=(None,1),name = 'y-input')#定义神经网络前向传播过程a = tf.matmul(x,w1)y = tf.matmul(a,w2)#定义损失函数和反向传播的算法cross_entropy = -tf.reduce_mean(y_*tf.log(tf.clip_by_value(y,1e-10,1.0)))train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy)#通过随机函数生成一个模拟数据集rdm = RandomState(1)dataset_size = 128X = rdm.rand(dataset_size,2)Y = [[int(x1+x2 < 1)] for (x1,x2) in X]with tf.Session() as sess:    init_op = tf.global_variables_initializer()    sess.run(init_op)    print (sess.run(w1))    print (sess.run(w2))    STEPS = 5000    for i in range(STEPS):        start = (i * batch_size) % dataset_size        end = min(start+batch_size,dataset_size)        #通过选取的样本训练神经网络并更新参数        sess.run(train_step,feed_dict={x:X[start:end],y_:Y[start:end]})        if i %1000 == 0:            total_cross_entropy = sess.run(cross_entropy,feed_dict={x:X,y_:Y})            print('after %d trainning step(s),cross entrop on all data is %g'                  %(i,total_cross_entropy))    print (sess.run(w1))    print (sess.run(w2))

张量是Tensorflow的数据模型，其中输入和输出都应该是张量···张量是什么意思呢···好像不太清楚样，但是没关系····张量本身并没有存储任何数据，它只是对运算结果的引用。
有个Tensorflow游乐场可以帮助大家更好的理解神经网络
http://playground.tensorflow.org