Tensorflow 如何理解'；维特比解码&x27；在张量流中

HMM中使用的传统viterbi算法有一个开始概率矩阵（），而tensorflow中的viterbi_解码参数只需要转移概率矩阵和发射概率矩阵。如何理解它

def viterbi_decode(score, transition_params):
  """Decode the highest scoring sequence of tags outside of 
  TensorFlow.

  This should only be used at test time.

  Args:
    score: A [seq_len, num_tags] matrix of unary potentials.
    transition_params: A [num_tags, num_tags] matrix of binary potentials.

  Returns:
    viterbi: A [seq_len] list of integers containing the highest scoring tag
    indicies.
    viterbi_score: A float containing the score for the Viterbi 
    sequence.
  """

---

Tensorflow中的viterbi算法不需要初始概率矩阵，因为它通过为所有状态提供零概率来开始解码

这意味着它从状态0开始

---

您可以查看实现。

我已经创建了关于tensorflow的viterbi算法的完整详细教程，示例如下：

假设您的数据如下所示：

# logits :       A [batch_size, max_seq_len, num_tags] tensor of unary potentials to use as input to the CRF layer.

# labels_a :     A [batch_size, max_seq_len] matrix of tag indices for which we compute the log-likelihood.

# sequence_len : A [batch_size] vector of true sequence lengths.

然后

现在我们可以计算维特比分数：

# score: A [seq_len, num_tags] matrix of unary potentials.
# transition_params: A [num_tags, num_tags] matrix of binary potentials.

# score: A [seq_len, num_tags] matrix of unary potentials.
# transition_params: A [num_tags, num_tags] matrix of binary potentials.