0

我正在研究基于 Tensorflow 的成本敏感型神经网络。但是由于Tensorflow的静态图结构。一些NN结构我自己无法实现。

我的损失函数(成本)、成本矩阵和计算过程描述如下,我的目标是计算总成本,然后优化 NN:

近似计算进度: 在此处输入图像描述

  • y_是具有形状的 CNN 的最后一个全连接输出(1024,5)
  • they是一个张量,其形状为 (1024),表示x[i]
  • 表示被分类的y_soft[i] [j]概率x[i]j

我如何在 Tensorflow 中实现这一点?

4

1 回答 1

0

成本矩阵:

[[0,1,100],
[1,0,1],
[1,20,0]]

标签:

[1,2]

你*:

[[0,1,0],
[0,0,1]]

y(预测):

[[0.2,0.3,0.5],
[0.1,0.2,0.7]]

标签,成本矩阵-->成本嵌入:

[[1,0,1],
[1,20,0]]

显然 [0.2,0.3,0.5] 中的 0.3 是指 [0,1,0] 的正确标签概率,因此它不应导致损失。

[0.1,0.2,0.7] 中的 0.7 是相同的。换句话说,y* 中值为 1 的 pos 不会导致损失。

所以我有(1-y *):

[[1,0,1],
[1,1,0]]

那么熵就是target*log(predict) + (1-target) * log(1-predict),y*中的值为0,应该用(1-target)*log(1-predict),所以我用( 1-预测)说(1-y)

1岁:

[[0.8,*0.7*,0.5],
[0.9,0.8,*0.3*]]

(斜体 num 没用)

自定义损失是

[[1,0,1], [1,20,0]]   *   log([[0.8,0.7,0.5],[0.9,0.8,0.3]])    *  
[[1,0,1],[1,1,0]]

你可以看到 (1-y*) 可以放在这里

所以损失是 -tf.reduce_mean(cost_embedding*log(1-y)) ,使其适用,应该是:

-tf.reduce_mean(cost_embedding*log(tf.clip((1-y),1e-10)))

演示如下

import tensorflow as tf
import numpy as np
hidden_units = 50
num_class = 3
class Model():
    def __init__(self,name_scope,is_custom):
        self.name_scope = name_scope
        self.is_custom = is_custom
        self.input_x = tf.placeholder(tf.float32,[None,hidden_units])
        self.input_y = tf.placeholder(tf.int32,[None])

        self.instantiate_weights()
        self.logits = self.inference()
        self.predictions = tf.argmax(self.logits,axis=1)
        self.losses,self.train_op = self.opitmizer()

    def instantiate_weights(self):
        with tf.variable_scope(self.name_scope + 'FC'):
            self.W = tf.get_variable('W',[hidden_units,num_class])
            self.b = tf.get_variable('b',[num_class])

            self.cost_matrix = tf.constant(
                np.array([[0,1,100],[1,0,100],[20,5,0]]),
                dtype = tf.float32
            )

    def inference(self):
        return tf.matmul(self.input_x,self.W) + self.b

    def opitmizer(self):
        if not self.is_custom:
            loss = tf.nn.sparse_softmax_cross_entropy_with_logits\
                (labels=self.input_y,logits=self.logits)
        else:
            batch_cost_matrix = tf.nn.embedding_lookup(
                self.cost_matrix,self.input_y
            )
            loss = - tf.log(1 - tf.nn.softmax(self.logits))\
                     * batch_cost_matrix

        train_op = tf.train.AdamOptimizer().minimize(loss)
        return loss,train_op

import random
batch_size = 128
norm_model = Model('norm',False)
custom_model = Model('cost',True)
split_point = int(0.9 * dataset_size)
train_set = datasets[:split_point]
test_set = datasets[split_point:]


with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(100):
        batch_index = random.sample(range(split_point),batch_size)
        train_batch = train_set[batch_index]
        train_labels = lables[batch_index]
        _,eval_predict,eval_loss = sess.run([norm_model.train_op,
                  norm_model.predictions,norm_model.losses],
                  feed_dict={
                      norm_model.input_x:train_batch,
                      norm_model.input_y:train_labels
        })
        _,eval_predict1,eval_loss1 = sess.run([custom_model.train_op,
                  custom_model.predictions,custom_model.losses],
                  feed_dict={
                      custom_model.input_x:train_batch,
                      custom_model.input_y:train_labels
        })
        # print 'norm',eval_predict,'\ncustom',eval_predict1
        print np.sum(((eval_predict == train_labels)==True).astype(np.int)),\
            np.sum(((eval_predict1 == train_labels)==True).astype(np.int))
        if i%10 == 0:
            print  'norm_test',sess.run(norm_model.predictions,
                  feed_dict={
                      norm_model.input_x:test_set,
                      norm_model.input_y:lables[split_point:]
        })
            print  'custom_test',sess.run(custom_model.predictions,
                  feed_dict={
                      custom_model.input_x:test_set,
                      custom_model.input_y:lables[split_point:]
        })
于 2017-12-06T06:57:26.993 回答