简单神经网络解决二分类问题示例（Tensorflow）（自定义损失函数）
在预测商品销量时，如果预测多了，商家损失的是生产商品的成本;而如果预测少了，损失的则是商品的利润。针对这种模型可以自己定义损失函数。
自定义损失函数为：
Loss(y,y′)=∑i=1nf(yi,y′i),f(x,y)={ a(x−y);x>yb(y−x);x y b ( y − x ) ; x <= y
可使用如下代码实现：
loss_less = 10loss_more = 1loss = tf.reduce_sum(tf.where(tf.greater(y, y_), (y - y_) * loss_more, (y_ - y) * loss_less))
整体代码如下：
#coding:utf-8import tensorflow as tffrom numpy.random import RandomStatebatch_size = 8x = tf.placeholder(tf.float32, shape = (None, 2), name = 'x-input')y_ = tf.placeholder(tf.float32, shape = (None, 1), name = 'y-input')w1 = tf.Variable(tf.random_normal([2,1],stddev = 1, seed = 1))y = tf.matmul(x, w1)loss_less = 10loss_more = 1loss = tf.reduce_sum(tf.where(tf.greater(y, y_), (y - y_) * loss_more, (y_ - y) * loss_less))train_step = tf.train.AdamOptimizer(0.001).minimize(loss)rdm = RandomState(1)dataset_size = 128X = rdm.rand(dataset_size, 2)Y = [[x1 + x2 + rdm.rand()/10.0-0.05] for (x1, x2) in X]with tf.Session() as sess: init_op = tf.initialize_all_variables() sess.run(init_op) STEPS = 5000 for i in range(STEPS): start = (i * batch_size) % dataset_size end = min(start+batch_size, dataset_size) sess.run(train_step, feed_dict={x : X[start:end], y_ : Y[start:end]}) print(sess.run(w1))【文章原创作者：美国服务器 http://www.558idc.com/mg.html提供，感恩】