Question

以下网络代码应该是您经典的简单LSTM语言模型，在一段时间后开始输出nan损失...在我的训练集上需要几个小时而且我无法在较小的数据集上轻松复制它。但它总是在严肃的训练中发生。

Sparse_softmax_with_cross_entropy应该是数值稳定的，所以它不是原因...但除此之外，我没有看到任何其他节点可能导致图中的问题。可能是什么问题？

class MyLM():
    def __init__(self, batch_size, embedding_size, hidden_size, vocab_size):
        self.x = tf.placeholder(tf.int32, [batch_size, None])  # [batch_size, seq-len]
        self.lengths = tf.placeholder(tf.int32, [batch_size])  # [batch_size]

        # remove padding. [batch_size * seq_len] -> [batch_size * sum(lengths)]
        mask = tf.sequence_mask(self.lengths)  # [batch_size, seq_len]
        mask = tf.cast(mask, tf.int32)  # [batch_size, seq_len]
        mask = tf.reshape(mask, [-1])  # [batch_size * seq_len]

        # remove padding + last token. [batch_size * seq_len] -> [batch_size * sum(lengths-1)]
        mask_m1 = tf.cast(tf.sequence_mask(self.lengths - 1, maxlen=tf.reduce_max(self.lengths)), tf.int32)  # [batch_size, seq_len]
        mask_m1 = tf.reshape(mask_m1, [-1])  # [batch_size * seq_len]

        # remove padding + first token.  [batch_size * seq_len] -> [batch_size * sum(lengths-1)]
        m1_mask = tf.cast(tf.sequence_mask(self.lengths - 1), tf.int32)  # [batch_size, seq_len-1]
        m1_mask = tf.concat([tf.cast(tf.zeros([batch_size, 1]), tf.int32), m1_mask], axis=1)  # [batch_size, seq_len]
        m1_mask = tf.reshape(m1_mask, [-1])  # [batch_size * seq_len]

        embedding = tf.get_variable("TokenEmbedding", shape=[vocab_size, embedding_size])
        x_embed = tf.nn.embedding_lookup(embedding, self.x)  # [batch_size, seq_len, embedding_size]

        lstm = tf.nn.rnn_cell.LSTMCell(hidden_size, use_peepholes=True)

        # outputs shape: [batch_size, seq_len, hidden_size]
        outputs, final_state = tf.nn.dynamic_rnn(lstm, x_embed, dtype=tf.float32,
                                                 sequence_length=self.lengths)
        outputs = tf.reshape(outputs, [-1, hidden_size])  # [batch_size * seq_len, hidden_size]

        w = tf.get_variable("w_out", shape=[hidden_size, vocab_size])
        b = tf.get_variable("b_out", shape=[vocab_size])
        logits_padded = tf.matmul(outputs, w) + b  # [batch_size * seq_len, vocab_size]
        self.logits = tf.dynamic_partition(logits_padded, mask_m1, 2)[1]  # [batch_size * sum(lengths-1), vocab_size]

        predict = tf.argmax(logits_padded, axis=1)  # [batch_size * seq_len]
        self.predict = tf.dynamic_partition(predict, mask, 2)[1]  # [batch_size * sum(lengths)]

        flat_y = tf.dynamic_partition(tf.reshape(self.x, [-1]), m1_mask, 2)[1]  # [batch_size * sum(lengths-1)]

        self.cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=self.logits, labels=flat_y)
        self.cost = tf.reduce_mean(self.cross_entropy)
        self.train_step = tf.train.AdamOptimizer(learning_rate=0.01).minimize(self.cost)

Answer 1

可能是exploding gradients的情况，其中梯度可能在LSTM中的反向传播期间爆炸，导致数字溢出。处理爆炸渐变的常用技术是执行Gradient Clipping。

Answer 2

检查输入到模型的列，在我的情况下，有一列具有NaN值的列，在删除NaN之后，它起作用了

张量流LSTM模型中的NaN损失

2 个答案: