quickdraw-dataset

Implementation of Quickdraw - an online game developed by Google

Implementation of QuickDraw - an online game developed by Google, combined with AirGesture - a simple gesture recognition application

Model and Android app for sketch recognition using Google's quickdraw dataset

A game where players compete to draw differing prompts on a shared canvas, as scored by a computer vision model

An easy to read and Object Oriented implementation of a simple Neural Network using back-propagation and hidden layers, applied on a basic image classification problem.

PyTorch implementation of the conditional Deep Convolutional Generative Adversarial Networks (cDCGAN) for the Google's "Quick, Draw!" dataset.

Web app to detect user hand-drawn sketches on a canvas. Using google's quickdraw dataset. App built using python with flask and keras API.

Keras light-weight model for sketch images classification using Quick!Draw dataset

CDCGAN Generator and ResNet34 Classifier for QuickDraw! dataset from Google

Yet another disentangled VAE ... but for quick drawing doodles

This project tries to create new doodles using GAN. This project uses google's quick draw data set

Neural network built from scratch for classifying Quick, Draw! doodles. Work in progress combining CNN and DNN, trained on a subset of figures.

Convolutional Neural Network trained to classify hand-drawn images

Implementation of Google's QuickDraw Game, instead of drawing on screen, drawing is done in air, and i used CNN to create the model. This is just an experimental project.

Implementation of a Generative Adversarial Network (GAN) to create synthetic images from Google’s Quick Draw dataset. This project explores adversarial training, dataset preprocessing, and critical evaluation of generative models.

Conditional GAN for the quickdraw dataset

ndjsonTosvg to convert Google Quickdraw data set ndjson format to svg i mages

A real-time symbolic recognition system using a Deep Convolutional Neural Network (CNN). Features a decoupled Flask-Electron architecture for low-latency (<200ms) sketch classification across 15 categories with built-in confidence thresholding.