RandAugment for Image Classification

RandAugment for Image Classification

Demonstrates RandAugment, a random data augmentation method for image classification, with a Keras model in a Gradio page and four sample pictures. For machine learning learners.

Made by keras-io on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Gradio app demonstrates RandAugment, a way of applying random changes to training images so a classifier learns to cope with variation. The record names one model, randaugment, from the keras-io group. Four sample pictures are included: an airplane, a car, a cat and a horse.

Who it suits: It suits machine learning learners who want to see data augmentation in action, and developers who want a small Gradio example around a Keras model. The record does not describe the output, so open the page to see it.

Industry | Who uses it | How they use it | Example
Education | Machine learning students | See how augmentation changes a training image | Run the cat picture and view the result
Research | Vision practitioners | Get a feel for augmentation before using it in training | Compare outputs for the four sample pictures
Software | Python developers | Read a small Gradio demo around a Keras model | Open app.py and requirements.txt

You can skip it if you need a training pipeline, since this is a demo page.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• Windows, macOS or Linux with Python, from a downloaded copy

Use case | Who | What they get back
See augmentation on a picture | Learners | A changed version of the image
Try the bundled samples | Anyone | A quick look at several example classes
Reuse as a base | Developers | A small Gradio app around a Keras model

How to set it up:

• Nothing at all if you use the online Space
• Python on your computer, only if you run a copy
• The packages listed in requirements.txt

1. Open the Space's page in a browser to use it with nothing to install.
2. To run a copy, install the Hugging Face Hub package and download the Space.
3. Move into the new folder, then install Gradio and the listed requirements.
4. Start the app with Python.

pip install -U huggingface_hub
hf download keras-io/randaugment --repo-type space --local-dir randaugment
cd randaugment
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Online, open the Space and use the controls on its page. On your own machine, run the main file from the Space folder, then use the page it serves. The four sample pictures are the quickest way to try it.

python app.py

Example: You open the Space and pick the horse picture. The app applies the method and shows the result on the page, possibly with the model's prediction. The record does not describe the output, so check the page.

For newcomers and experts: Data augmentation means making altered copies of training images, such as rotated or recolored ones, so a model sees more variety. Start by opening the Space and running a sample picture.

If you know the field, RandAugment picks a small number of random operations from a fixed set and applies them at a set strength, which avoids a costly search for augmentation policies. The record gives no settings or accuracy figures.

You pick or upload a picture
The app applies random augmentations
The Keras model may classify the result
The page shows the output

Good to know:

• License: Apache 2, as listed on the Space
• Cost to run: none named
• Data it reaches: the pictures you give it and the four samples in the repository
• Not for: the record names no exclusions, and it gives no accuracy figures

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/keras-io/randaugment
• Files: https://huggingface.co/spaces/keras-io/randaugment/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.