tensorflow进阶篇-4(损失函数2)

Hinge损失函数主要用来评估支持向量机算法，但有时也用来评估神经网络算法。下面的示例中是计算两个目标类(-1,1)之间的损失。下面的代码中，使用目标值1，所以预测值离1越近，损失函数值越小：

# Use for predicting binary (-1, 1) classes
# L = max(0, 1 - (pred * actual))
hinge_y_vals = tf.maximum(0., 1. - tf.multiply(target, x_vals))
hinge_y_out = sess.run(hinge_y_vals)

两类交叉函数熵损失函数(Cross-entropy loss)有时也作为逻辑损失函数，比如，当预测两类目标0或者1时，希望度量函数预测值到真实分类值(0或者1)的距离，这个距离经常是0到1之间的实数。

 

# L = -actual * (log(pred)) - (1-actual)(log(1-pred))
xentropy_y_vals = - tf.multiply(target, tf.log(x_vals)) - tf.multiply((1. - target), tf.log(1. - x_vals))
xentropy_y_out = sess.run(xentropy_y_vals)

 

Sigmoid交叉熵损失函数与上一个损失函数非常类似，有一点不同的是，它先把想x_vals值通过sigmoid函数转换，再计算交叉熵损失：

 

# L = -actual * (log(sigmoid(pred))) - (1-actual)(log(1-sigmoid(pred)))
# or
# L = max(actual, 0) - actual * pred + log(1 + exp(-abs(actual)))
xentropy_sigmoid_y_vals = tf.nn.sigmoid_cross_entropy_with_logits(logits=x_vals, labels=targets)
xentropy_sigmoid_y_out = sess.run(xentropy_sigmoid_y_vals)

 

加权交叉熵损失函数(Weighted cross entropy loss)是Sigmoid交叉熵损失函数的加权，对正目标加权。

 

# L = -actual * (log(pred)) * weights - (1-actual)(log(1-pred))
# or
# L = (1 - pred) * actual + (1 + (weights - 1) * pred) * log(1 + exp(-actual))
weight = tf.constant(0.5) #正目标加权 权值为0.5
xentropy_weighted_y_vals = tf.nn.weighted_cross_entropy_with_logits(logits=x_vals,targets=targets, pos_weight=weight)
xentropy_weighted_y_out = sess.run(xentropy_weighted_y_vals)

 

利用matplotlib绘画出以上的损失函数为：

 

完整代码：

import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
ops.reset_default_graph()

# Create graph
sess = tf.Session()

x_vals = tf.linspace(-3., 5., 500)
target = tf.constant(1.)
targets = tf.fill([500,], 1.)

# Hinge loss
# Use for predicting binary (-1, 1) classes
# L = max(0, 1 - (pred * actual))
hinge_y_vals = tf.maximum(0., 1. - tf.multiply(target, x_vals))
hinge_y_out = sess.run(hinge_y_vals)

# Cross entropy loss
# L = -actual * (log(pred)) - (1-actual)(log(1-pred))
xentropy_y_vals = - tf.multiply(target, tf.log(x_vals)) - tf.multiply((1. - target), tf.log(1. - x_vals))
xentropy_y_out = sess.run(xentropy_y_vals)

# Sigmoid entropy loss
# L = -actual * (log(sigmoid(pred))) - (1-actual)(log(1-sigmoid(pred)))
# or
# L = max(actual, 0) - actual * pred + log(1 + exp(-abs(actual)))
xentropy_sigmoid_y_vals = tf.nn.sigmoid_cross_entropy_with_logits(logits=x_vals, labels=targets)
xentropy_sigmoid_y_out = sess.run(xentropy_sigmoid_y_vals)

# Weighted (softmax) cross entropy loss
# L = -actual * (log(pred)) * weights - (1-actual)(log(1-pred))
# or
# L = (1 - pred) * actual + (1 + (weights - 1) * pred) * log(1 + exp(-actual))
weight = tf.constant(0.5)
xentropy_weighted_y_vals = tf.nn.weighted_cross_entropy_with_logits(logits=x_vals,targets=targets, pos_weight=weight)
xentropy_weighted_y_out = sess.run(xentropy_weighted_y_vals)

# Plot the output
x_array = sess.run(x_vals)
plt.plot(x_array, hinge_y_out, 'b-', label='Hinge Loss')
plt.plot(x_array, xentropy_y_out, 'r--', label='Cross Entropy Loss')
plt.plot(x_array, xentropy_sigmoid_y_out, 'k-.', label='Cross Entropy Sigmoid Loss')
plt.plot(x_array, xentropy_weighted_y_out, 'g:', label='Weighted Cross Entropy Loss (x0.5)')
plt.ylim(-1.5, 3)
#plt.xlim(-1, 3)
plt.legend(loc='lower right', prop={'size': 11})
plt.show()

Softmax交叉熵损失函数(Softmax cross-entropy loss)是作用于非归一化的输出结果只针对单个目标分类的计算损失。通过softmax函数将输出结果转化成概率分布，然后计算真值概率分布的损失：

# Softmax entropy loss
# L = -actual * (log(softmax(pred))) - (1-actual)(log(1-softmax(pred)))
unscaled_logits = tf.constant([[1., -3., 10.]])
target_dist = tf.constant([[0.1, 0.02, 0.88]])
softmax_xentropy = tf.nn.softmax_cross_entropy_with_logits(logits=unscaled_logits, labels=target_dist)
print(sess.run(softmax_xentropy))

输出：[ 1.16012561]

稀疏Softmax交叉熵损失函数(Sparse Softmax cross-entropy loss)和上一个损失函数类似，它是把目标函数分类为true的转化成index，而Softmax交叉熵损失函数将目标转成概率分布：

# Sparse entropy loss
# L = sum( -actual * log(pred) )
unscaled_logits = tf.constant([[1., -3., 10.]])
sparse_target_dist = tf.constant([2])
sparse_xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=unscaled_logits, labels=sparse_target_dist)
print(sess.run(sparse_xentropy))

输出：[ 0.00012564]

 

两类交叉熵损失函数有时也作为逻辑损失函数。