fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing data operation costs, all with unmatched scalability.

Invert and perturb GAN images for test-time ensembling

TorchFlare is a simple, beginner-friendly, and easy-to-use PyTorch Framework train your models effortlessly.

Scaling Object Detection by Transferring Classification Weights

A lightweight and extensible toolbox for image classification

Code release for "A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation", accepted by CVPR2023.

Web Based Image Recognition System in Python Flask

Protein localization in cell microscopy images Kaggle competition

CenOTAPH: COlour and Texture Analysis toolbox for PytHon

[CVPR 2019] SketchGAN: Joint Sketch Completion and Recognition with Generative Adversarial Network

🍎 Fruits Classification App (Gradio) 🍌

Implementations of various classifiers on MNIST dataset. Both traditional machine learning and deep learning methods are included.

Deep Learning for Image Classification

Hand-on experience in image classification by deep nerual network

Retrain a pre-trained Neural Network to recognize Images

Image classification using deep learning models with activation map visualisation and TensorRT support