🏆 Take the free Top-Rated Session from TechXchange in Las Vegas and Build Your First GenAI Application the Right Way! Learn more

Offered By: IBMSkillsNetwork

Image classification Using hugging face for Crypto Beans

The characteristics of currency are durability, portability, divisibility, uniformity, limited supply, and acceptability; all these describe beans. You are a founder of a Crypto company BeanStock that uses beans to back up crypto tokens. The token has exploded in popularity, so you need different beans for different tokens. Sorting the beans is difficult, so you fine-tune Hugging Face's pre-trained Transformers and PyTorch vision on bean dataset, getting state-of-the-art performance.

Continue reading

Guided Project

Computer Vision

567 Enrolled
4.3
(148 Reviews)

At a Glance

The characteristics of currency are durability, portability, divisibility, uniformity, limited supply, and acceptability; all these describe beans. You are a founder of a Crypto company BeanStock that uses beans to back up crypto tokens. The token has exploded in popularity, so you need different beans for different tokens. Sorting the beans is difficult, so you fine-tune Hugging Face's pre-trained Transformers and PyTorch vision on bean dataset, getting state-of-the-art performance.

About

The characteristics of currency are durability, portability, divisibility, uniformity, limited supply, and acceptability; all these describe beans. You are a founder of a Crypto company BeanStock that uses beans to back up crypto tokens. The token has exploded in popularity, so you need different beans for different tokens. Sorting the beans is difficult, so you fine-tune Hugging Face's pre-trained Transformers on your bean dataset, getting state-of-the-art performance.
You first train your Transformers to classify traffic signals then move on to the big problem of bean classification. beans_img_3leaf.png 745 KB

Why you should do this Guided Project

You can learn how to train and fit the Hugging Face Transformers model.  Here we are using the model Vision Transformer Model for Binary Classification as well as Multi-Class Image Classification. The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over patches of the image. An image is split into fixed-size patches, each of them is then linearly embedded, position embeddings are added, and the resulting sequence of vectors is fed to a standard Transformer encoder with the Help of   PyTorch vision.


A Look at the Project Ahead

Tell your audience what they can expect to learn. Better yet, tell them what they will be able to do as a result of completing your project:
  • How to use hugging Face API
  • Vision Transformer Model
  • Image Classification

What You'll Need

To complete this guided project, you will need a basic understanding of the working mechanics of Python. You will also need some prior experience working with Pre-trained Models. It will be more helpful if you have prior knowledge of the Hugging Face Transformer. 
Remember that the IBM Skills Network Labs environment comes with many things pre-installed (e.g. Docker) to save them the hassle of setting everything up. Also note that this platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari.

Estimated Effort

1 Hour

Level

Intermediate

Industries

Information Technology

Skills You Will Learn

Artificial Intelligence, Computer Vision, Image Processing, Python, PyTorch

Language

English

Course Code

GPXX0RR9EN

Tell Your Friends!

Saved this page to your clipboard!

This Guided Project is part of the following Learning Paths

Have questions or need support? Chat with me 😊