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.

Repositório dos exemplos e desafios utilizados na disciplina de Visão Computacional do curso de MBA Machine Learning da FIAP

Scaling Object Detection by Transferring Classification Weights

A lightweight and extensible toolbox for image classification

The binary classification problem focused on first IEEE Image forensics challenge-phase 1, to predict the given image is pristine or manipulated/edited/fake. Comparing CNN & Transfer Learning models for the problem and boosting the performance by feature extraction

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.

Tensorflow 版本的图片鉴黄。not suitable/safe for work (NSFW) images detection using Tensorflow

Web Based Image Recognition System in Python Flask

Deploy AutoML models for image classification on AWS Sagemaker with AutoGluon

This repository contains demonstrations done with deep learning computer vision models.

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

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

Awesome list of papers on sea ice, covering semi-supervised learning and supervised learning

Deep Learning for Image Classification

Develop an AI-based image classification system using CNN and transfer learning. The project includes data preprocessing, model training, fine-tuning, evaluation with precision, recall, and F1-score, and testing.

In this case study, I combine several subcategories of data not based on item color but based on item type. These types will be classified into types of clothing and shoes. The result of merging these subcategories is that there are several main categories which are divided into 5 categories, namely Dress, Pants, Shirt, Shoes, Shorts. I'm trying…