TensorFlow学习笔记

最新推荐文章于 2022-07-10 17:07:41 发布

Johnson0722

最新推荐文章于 2022-07-10 17:07:41 发布

阅读量557

点赞数

CC 4.0 BY-SA版权

分类专栏： TensorFlow 文章标签： TF-Hub Tensorflow 深度学习人工智能

本文链接：https://blog.youkuaiyun.com/John_xyz/article/details/80666182

TensorFlow 专栏收录该内容

4 篇文章

订阅专栏

本文介绍了TensorFlow中Estimator API的功能与使用方法，并详细探讨了TensorFlow Hub提供的预训练模型资源，包括文本分类任务中使用的通用句子编码器等。通过实例展示了如何利用这些模块进行迁移学习。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Estimater

Estimator：代表一个完整的模型。Estimator API 提供一些方法来训练模型、判断模型的准确率并生成预测。

TF-Hub

https://www.tensorflow.org/hub/

TensorFlow Hub is a library to foster the publication, discovery, and consumption of reusable parts of machine learning models. A module is a self-contained piece of a TensorFlow graph, along with its weights and assets, that can be reused across different tasks in a process known as transfer learning.

1. text classification

sentence embedding models: Universal sentence encoder https://www.tensorflow.org/hub/modules/google/universal-sentence-encoder/1

Transformer
DAN（Deep average network）

Example

import tensorflow as tf
import tensorflow_hub as hub

with tf.Graph().as_default():
  embed = hub.Module("https://tfhub.dev/google/nnlm-en-dim128-with-normalization/1")
  embeddings = embed(["A long sentence.", "single-word", "http://example.com"])

  with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    sess.run(tf.tables_initializer())

    print(sess.run(embeddings))