Fine Tune BERT for Text Classification with TensorFlow

4.6
106 个评分
提供方
6,210 人已注册
在此免费指导项目中,您将:

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

在面试中展现此实践经验

2.5 hours
中级
无需下载
分屏视频
英语(English)
仅限桌面

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. Prerequisites: In order to successfully complete this project, you should be competent in the Python programming language, be familiar with deep learning for Natural Language Processing (NLP), and have trained models with TensorFlow or and its Keras API. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

必备条件

It is assumed that are competent in Python programming and have prior experience with building deep learning NLP models with TensorFlow or Keras

您要培养的技能

  • natural-language-processing

  • Tensorflow

  • machine-learning

  • deep-learning

  • BERT

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:

  1. Introduction to the Project

  2. Setup your TensorFlow and Colab Runtime

  3. Download and Import the Quora Insincere Questions Dataset

  4. Create tf.data.Datasets for Training and Evaluation

  5. Download a Pre-trained BERT Model from TensorFlow Hub

  6. Tokenize and Preprocess Text for BERT

  7. Wrap a Python Function into a TensorFlow op for Eager Execution

  8. Create a TensorFlow Input Pipeline with tf.data

  9. Add a Classification Head to the BERT hub.KerasLayer

  10. Fine-Tune and Evaluate BERT for Text Classification

指导项目工作原理

您的工作空间就是浏览器中的云桌面,无需下载

在分屏视频中,您的授课教师会为您提供分步指导

授课教师

审阅

来自FINE TUNE BERT FOR TEXT CLASSIFICATION WITH TENSORFLOW的热门评论

查看所有评论

常见问题

由于您的工作空间包含适合笔记本电脑或台式计算机使用的云桌面,因此指导项目不在移动设备上提供。

指导项目授课教师是特定领域的专家,他们在项目的技能、工具或领域方面经验丰富,并且热衷于分享自己的知识以影响全球数百万的学生。

您可以从指导项目中下载并保留您创建的任何文件。为此,您可以在访问云桌面时使用‘文件浏览器’功能。

您可在页面顶部点按此指导项目的经验级别,查看任何知识先决条件。对于指导项目的每个级别,您的授课教师会逐步为您提供指导。

是,您可以在浏览器的云桌面中获得完成指导项目所需的一切。

您可以直接在浏览器中于分屏环境下完成任务,以此从做中学。在屏幕的左侧,您将在工作空间中完成任务。在屏幕的右侧,您将看到有授课教师逐步指导您完成项目。

还有其他问题吗?请访问 学生帮助中心