Transfer Learning for NLP with TensorFlow Hub

提供方
Coursera Project Network
在此指导项目中,您将:

Use pre-trained NLP text embedding models from TensorFlow Hub

Perform transfer learning to fine-tune models on real-world text data

Visualize model performance metrics with TensorBoard

Clock1.5 hours
Intermediate中级
Cloud无需下载
Video分屏视频
Comment Dots英语(English)
Laptop仅限桌面

This is a hands-on project on transfer learning for natural language processing with TensorFlow and TF Hub. By the time you complete this project, you will be able to use pre-trained NLP text embedding models from TensorFlow Hub, perform transfer learning to fine-tune models on real-world data, build and evaluate multiple models for text classification with TensorFlow, and visualize model performance metrics with Tensorboard. 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.

您要培养的技能

Natural Language ProcessingDeep LearningInductive TransferMachine LearningTensorflow

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 and Project Overview

  2. Setup your TensorFlow and Colab GPU Runtime

  3. Download and Import the Quora Insincere Questions Dataset

  4. TensorFlow Hub for Natural Language Processing

  5. Define Function to Build Models

  6. Compile Models

  7. Train Various Text Classification Models

  8. Compare Accuracy and Loss Curves

  9. Fine-tune Model from TF Hub

  10. Train Bigger Models and Visualize Metrics with TensorBoard

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

常见问题

常见问题

还有其他问题吗?请访问 学生帮助中心