sayannath/ViT-TF-Hub-Application

Build and fine-tune your Image Classifier using a Vision Transformer Model from TensorFlow Hub

28
/ 100
Experimental

This project helps machine learning practitioners fine-tune an image classification model to recognize different scenes in images. You provide a dataset of images, and it outputs a highly accurate model capable of categorizing new, unseen images into various scene types. This is ideal for data scientists, ML engineers, or researchers working on visual recognition tasks.

No commits in the last 6 months.

Use this if you need to build a custom image classifier for scene detection, leveraging powerful Vision Transformer models with a focus on high accuracy.

Not ideal if you are a beginner looking for a simple drag-and-drop tool, as this requires some familiarity with machine learning workflows and TensorFlow.

image-classification scene-detection computer-vision machine-learning-engineering deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 27, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sayannath/ViT-TF-Hub-Application"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.