text_classification_model_han.py 文件源码

def _embed_sequence_with_length(self, embeddings, input_text):
        # calculate max length of the input_text
        mask_words = tf.greater(input_text, 0)  # true for words false for padding
        words_length = tf.reduce_sum(tf.cast(mask_words, tf.int32), -1)
        mask_sentences = tf.greater(words_length, 0)
        sentences_length = tf.reduce_sum(tf.cast(mask_sentences, tf.int32), 1)
        input_text = tf.add(input_text, 1)
        embedded_sequence = tf.nn.embedding_lookup(embeddings, input_text)
        return embedded_sequence, sentences_length, words_length