Generating New Recipes using GPT-2

4.5
20 个评分
提供方
Coursera Project Network
2,385 人已注册
在此免费指导项目中,您将:

Clean and preprocess text data for modeling

Create datasets for large-scale language generation

Fine-tune large-scale language model on small and niche task of generating recipes

Showcase this hands-on experience in an interview

Clock90-120 minutes
Intermediate中级
Cloud无需下载
Video分屏视频
Comment Dots英语(English)
Laptop仅限桌面

In this 2 hour long project, you will learn how to preprocess a text dataset comprising recipes, and split it into a training and validation set. You will learn how to use the HuggingFace library to fine-tune a deep, generative model, and specifically how to train such a model on Google Colab. Finally, you will learn how to use GPT-2 effectively to create realistic and unique recipes from lists of ingredients based on the aforementioned dataset. This project aims to teach you how to fine-tune a large-scale model, and the sheer magnitude of resources it takes for these models to learn. You will also learn about knowledge distillation and its efficacy in use cases such as this one. 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

Intermediate Python users with some experience with Natural Language Processing and/or Machine Learning.

您要培养的技能

Python ProgrammingMachine LearningNatural Language Processing

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 task and demo

  2. Exploratory data analysis and visualizations

  3. Dataset preparation

  4. GPT-2 theory and related machine learning concepts

  5. Model training on Google Colab

  6. Evaluating model performance empirically

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

审阅

来自GENERATING NEW RECIPES USING GPT-2的热门评论

查看所有评论

常见问题

常见问题

还有其他问题吗?请访问 学生帮助中心