Rock-Paper-Scissors Classifier
A deep learning image classifier for rock, paper and scissors hand gestures, with over 99% validation accuracy.
- Status
- Finished and delivered. It does what it set out to do and no more work is planned.
- Kind
- Computer Vision
- Started
- May 2024

About it
The problem
Classifying hand gestures from photos is a compact computer vision problem that still exposes the real challenges: varied lighting, angles and backgrounds.
The approach
I trained a convolutional network with TensorFlow and Keras on a public dataset, using custom data generators and augmentation to make the model robust.
- Conv2D and MaxPooling layers with dropout and dense layers.
- Augmentation and a validation split to prevent overfitting.
- A prediction module for uploaded images, and plotted training history over 75 epochs.
The result
The model reaches 99.22% validation accuracy with low loss, and classifies new photos of rock, paper or scissors reliably.
What it does5
Dataset Processor
Model Builder
Training History Plot
Image Predictor
Performance Metrics
More work

Rone Arena API
A public FastAPI for Mobile Legends hero data, analytics and player tools, with a web playground and SDKs.

BeliMadu.com
An online honey shop on Next.js 16 and Cloudflare Workers, with a WhatsApp-checkout cart and a Vitest suite.

ridwaanhall.com
This site: a portfolio and blog on Next.js 16 with an admin, Markdown versions of every page and a CV generated from the About page.
Comments0
Signed-in readers can comment.