TensorFlow中使用tf.strings处理字符串型输入

一、tf.strings.to_hash_bucket_fast

该方法可以把每个字（词）进行hashing，编码到具体的对应索引上。

import tensorflow as tf

# str 字符串
# num 词表大小
tf.strings.to_hash_bucket_fast(str, num)

二、tf.lookup

三、tf.strings.unicode_decode

引用

【1】tf.strings：https://www.tensorflow.org/api_docs/python/tf/strings

【2】tf.strings.to_hash_bucket_fast：https://www.tensorflow.org/api_docs/python/tf/strings/to_hash_bucket_fast

【3】https://cloud.tencent.com/developer/article/1583795

【4】https://zhuanlan.zhihu.com/p/127077566

【5】How to Use Word Embedding Layers for Deep Learning with Keras：https://machinelearningmastery.com/use-word-embedding-layers-deep-learning-keras/

【6】https://pbpython.com/categorical-encoding.html

【7】https://machinelearningmastery.com/autoencoder-for-classification/