python - 我的分类器损失很大，准确率始终为 0

Question

我正在训练一个分类器以获得用于优化的因素。我的数据集一开始包含 800 个样本(有些相似，只是稍作修改)。

我在 GoogleColab 环境中使用 TensorFlow 开发了我的模型。

我为这个问题使用了一个简单的MLP，第一阶段有3 个隐藏层，每个层有 256 个节点。我也有 64 节课😬。

我有可变长度输入，我用"-1"填充解决了这个问题。

根据我的实际特征，我知道我会得到很差的精度，但我没想到零精度和非常大的损失。

这是我在省略了一些我注意到会对准确性产生负面影响的特征之后的数据集:

     0  1   2   4  5  6  8  9   11  13    15      17    19      21
805  6  10  11  1  3  1  6  64  2   1.0   64.0    64.0  64.0    -1.0
334  6  12  18  0  2  4  7  2   1   32.0  128.0   64.0  128.0   -1.0
781  7  10  11  1  3  1  6  2   2   2.0   64.0    32.0  32.0    64.0

[已编辑]:这是我的一些标签行:

    0
0   108
1   30
2   30
3   16
4   62
5   126
6   22
7   30
8   48

这是我的一组结果:

epoch[0] step [0] train -- loss : 50751.734375, accuracy : 0.0
epoch[0] step [100] train -- loss : 27310.064453125, accuracy : 0.0
epoch[0] step [200] train -- loss : 58120.6015625, accuracy : 0.0
epoch[0] step [300] train -- loss : 31801.9453125, accuracy : 0.0
epoch[0] step [400] train -- loss : 54360.76171875, accuracy : 0.0
epoch[0] step [500] train -- loss : 59946.67578125, accuracy : 0.0
epoch[1] step [0] train -- loss : 40612.06640625, accuracy : 0.0
epoch[1] step [100] train -- loss : 43229.734375, accuracy : 0.0
epoch[1] step [200] train -- loss : 36951.84375, accuracy : 0.0
epoch[1] step [300] train -- loss : 45225.828125, accuracy : 0.0
epoch[1] step [400] train -- loss : 47055.1796875, accuracy : 0.0
epoch[1] step [500] train -- loss : 54023.23046875, accuracy : 0.0

我想知道为什么我会得到这么大的损失，而且我的损失也不收敛 :(。

那些是我得到的准确率和损失的奇怪图表:

我的代码运行完美，但我仍然怀疑是不是我写得不好，所以弄​​得一团糟。

这是我代码的重要部分:

class MLP():
    '''
      This is the implementation of the Multi Layer Perceptron
    '''
    def __init__(self, x_train, y_train, n_classes, n_hiddens=3, activation=tf.nn.relu):
      ...       
    ################################ Create the model ##############################    
    def multilayer_perceptron(self,X):      
        # Hidden fully connected layer with n_hidden_1 neurons
        layer_1 = tf.layers.dense(inputs=X, units= self.n_hidden_1, use_bias=True, kernel_initializer=self._init, name= 'layer_1')
        layer_1 = tf.layers.batch_normalization(layer_1,training=self.is_train)
        layer_1 = self.activation(layer_1)     

        # Hidden fully connected layer with n_hidden_2 neurons
        layer_2 = tf.layers.dense(inputs=layer_1, units= self.n_hidden_2, use_bias=True, kernel_initializer=self._init, name= 'layer_2')
        layer_2 = tf.layers.batch_normalization(layer_2,training=self.is_train)
        layer_2 = self.activation(layer_2)   

        # Hidden fully connected layer with n_hidden_3 neurons
        layer_3 = tf.layers.dense(inputs=layer_2, units= self.n_hidden_3, use_bias=True, kernel_initializer=self._init, name= 'layer_3')
        layer_3 = tf.layers.batch_normalization(layer_3, training=self.is_train)
        layer_3 = self.activation(layer_3)  

        # Output fully connected layer with the output
        out_layer = tf.layers.dense(inputs=layer_3, units= self.n_classes, use_bias=True, kernel_initializer=self._init, name= 'out_layer')

        tf.summary.histogram('pre-activations', out_layer) 
        return layer_1, layer_2, layer_3, out_layer  

在这里我计算训练集的损失和准确性:

 def loss(self, X, Y):
        _, _, _, self.predicted_out = self.multilayer_perceptron(X) 
        print("Predicted out", self.predicted_out)
        with tf.name_scope('loss'):          
                loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=self.predicted_out, labels=Y))
        tf.summary.scalar('loss', loss) 

        with tf.name_scope('accuracy'):
                predicted_class = tf.nn.softmax(self.predicted_out)
                with tf.name_scope('correct_prediction'):
                    correct_prediction = tf.equal(tf.argmax(predicted_class, 1), tf.argmax(Y, 1))
                with tf.name_scope('accuracy'):
                    accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
        tf.summary.scalar('accuracy', accuracy)
        self.merged =  tf.summary.merge_all()

        return loss, accuracy 

这是训练的功能:

def train(self):
        self.train_writer = tf.summary.FileWriter('./Graph', self.sess.graph) 
    # training data
        train_input = self.Normalize(self.x_train)
        train_output = self.y_train.copy()

        save_sess=self.sess

      #costs history :
        costs = []
        costs_inter=[] 
      #for early stopping :
        best_cost=1000000
        stop = False
        last_improvement=0

        n_samples = train_input.shape[0] # size of the training set

       #train the mini_batches model using the early stopping criteria
        epoch = 0
        while epoch < self.max_epochs and stop == False:
            #train the model on the traning set by mini batches
            #suffle then split the training set to mini-batches of size self.batch_size
            seq =list(range(n_samples))
            random.shuffle(seq)
            mini_batches = [
                seq[k:k+self.batch_size]
                for k in range(0,n_samples, self.batch_size)
            ]

            avg_cost = 0. # The average cost of mini_batches
            step= 0

            for sample in mini_batches:                  
                batch_x = x_train.iloc[sample, :]
                batch_y =train_output.iloc[sample, :]
                feed_dict={self.X: batch_x,self.Y:batch_y, self.is_train:True}
                self.train_summary, _, cost,acc=self.sess.run([self.merged, self.train_step, self.loss_, self.accuracy_], feed_dict=feed_dict)
                avg_cost += cost *len(sample)/n_samples      
                print('epoch[{}] step [{}] train -- loss : {}, accuracy : {}'.format(epoch,step, cost, acc))
                self.train_writer.add_summary(self.train_summary, global_step=step)
                step += 100

            #cost history since the last best cost
            costs_inter.append(avg_cost)
            epoch +=1

        #Test the model 
        pred = tf.nn.softmax(self.predicted_out)  # Apply softmax to logits
        correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(self.Y, 1))
        # Calculate accuracy
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
        accuracy_test = self.sess.run([accuracy],feed_dict={self.X: x_test, self.Y: y_test,self.is_train:False})
        #print("Accuracy:", accuracy.eval({self.X: x_test, self.Y: y_test}))
        print("Accuracy_test : ", accuracy_test)

        # Writes the summaries to disk
        self.train_writer.flush()
        # Flushes the summaries to disk and closes the SummaryWriter
        self.train_writer.close()                              
        return costs

在这里我调用我的方法 train，我计划应用交叉验证来查看我是否可以提高模型的准确性，但我还没有:

def cross_validation(self,batch_size, n_hidden_1 , n_hidden_2, n_hidden_3, learning_rate):
        ##### Other parameter 
        self.batch_size = batch_size
        self.n_hidden_1 = n_hidden_1
        self.n_hidden_2 = n_hidden_2
        self.n_hidden_3 = n_hidden_3
        self.learning_rate = learning_rate
        self.require_improvement= 20
        self.max_epochs = 80
        self._init = tf.random_normal_initializer
        self.optimizer=tf.train.AdamOptimizer      
        loss = 0   
        tf.reset_default_graph()

        with tf.name_scope('input'):
          self.X=tf.placeholder("float",shape=[None,self.x_train.shape[1]])
          self.Y=tf.placeholder("float",shape=[None,self.y_train.shape[1]])
          self.is_train = tf.placeholder(tf.bool, name="is_train") 
        self.loss_, self.accuracy_ = self.loss(self.X, self.Y)
        self.train_step = self.optimizer(self.learning_rate).minimize(self.loss_)

        # Initiate a tensor session
        init = tf.global_variables_initializer()
        self.sess = tf.Session()
        self.sess.run(init)

        #train the model 
        loss = self.train()

        self.sess.close()
        del self.sess
        return  loss  

最后这是我的主要内容:

  if __name__=='__main__':
  tbc = tb.TensorBoardColab()
  mlp =   MLP(x_train, y_train, n_classes)
  loss= mlp.cross_validation(batch_size, n_hidden_1 , n_hidden_2, n_hidden_3, learning_rate) 

我原以为准确率会很差，但不是“0”，而且没有任何收敛的巨大损失让我震惊。谁能告诉我这里的问题在哪里？

Answer 1

有几点需要注意

1. 你应该在每次训练开始前删除tf摘要文件，因为根据你的代码全局步骤将从0重新开始

2. 您的损失函数是 softmax_cross_entropy_with_logits_v2，要使用它，您可能需要在 onehot 中编码您的标签，并尝试使用此函数中的内部 softmax 函数最小化靠近该 onehot 标签的 logit 层.如果您想保留当前的真实标签，请检查sparse_softmax_cross_entropy_with_logits .用法类似，但其中一些需要是 onehot 标签。查看详细说明here