This is a guided project on fine-tuning a Bidirectional Transformers for Language Understanding (BERT) model for text classification with TensorFlow. In this 2.5 hour long project, you will learn to preprocess and tokenize data for BERT classification, build TensorFlow input pipelines for text data with the tf.data API, and train and evaluate a fine-tuned BERT model for text classification with TensorFlow 2 and TensorFlow Hub.

Fine Tune BERT for Text Classification with TensorFlow

位教师:Snehan Kekre
访问权限由 New York State Department of Labor 提供
18,936 人已注册
您将学到什么
Build TensorFlow Input Pipelines for Text Data with the tf.data API
Tokenize and Preprocess Text for BERT
Fine-tune BERT for text classification with TensorFlow 2 and TensorFlow Hub
您将练习的技能
要了解的详细信息

添加到您的领英档案
仅桌面可用
了解顶级公司的员工如何掌握热门技能

在 2 小时内学习、练习并应用岗位必备技能
- 接受行业专家的培训
- 获得解决实训工作任务的实践经验
- 使用最新的工具和技术来建立信心

关于此指导项目
分步进行学习
在与您的工作区一起在分屏中播放的视频中,您的授课教师将指导您完成每个步骤:
-
Introduction to the Project
-
Setup your TensorFlow and Colab Runtime
-
Download and Import the Quora Insincere Questions Dataset
-
Create tf.data.Datasets for Training and Evaluation
-
Download a Pre-trained BERT Model from TensorFlow Hub
-
Tokenize and Preprocess Text for BERT
-
Wrap a Python Function into a TensorFlow op for Eager Execution
-
Create a TensorFlow Input Pipeline with tf.data
-
Add a Classification Head to the BERT hub.KerasLayer
-
Fine-Tune and Evaluate BERT for Text Classification
推荐体验
It is assumed that are competent in Python programming and have prior experience with building deep learning NLP models with TensorFlow or Keras
8个项目图片
位教师

提供方
学习方式
基于技能的实践学习
通过完成与工作相关的任务来练习新技能。
专家指导
使用独特的并排界面,按照预先录制的专家视频操作。
无需下载或安装
在预配置的云工作空间中访问所需的工具和资源。
仅在台式计算机上可用
此指导项目专为具有可靠互联网连接的笔记本电脑或台式计算机而设计,而不是移动设备。
人们为什么选择 Coursera 来帮助自己实现职业发展

Felipe M.

Jennifer J.

Larry W.

Chaitanya A.
学生评论
- 5 stars
70.75%
- 4 stars
20.75%
- 3 stars
4.71%
- 2 stars
1.41%
- 1 star
2.35%
显示 3/212 个
已于 Oct 6, 2020审阅
Need More detail explanation as its a advance NLP topic.
已于 Jun 19, 2021审阅
The project is very clear and easy to follow. Would suggest providing some gmail account so that we don't have to log into the colab using our own google credentials.
已于 Feb 1, 2023审阅
it is very helpful and simply explain the idea of Bert model , really it is useful project






