Hakjin Lee's Projects
A simple and extensible library to create Bayesian Neural Network layers on PyTorch.
Solutions for Codility training assignments in Python
Making large AI models cheaper, faster and more accessible
When mother raids Ghouls on the dark side of the moon.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Phaser 3 Open Source Dungeon Crawler Experiment
E(2)-Equivariant CNNs Library for Pytorch
A simple platformer made along the theme of Ludum Dare 28
Equivariant Steerable CNNs Library for Pytorch
FewX is an open-source toolbox on top of Detectron2 for data-limited instance-level recognition tasks.
Create UIs for your machine learning model in Python in 3 minutes
Interactive SAM Demo with Gradio
Build and train PyTorch models and connect them to the ML lifecycle using Lightning App templates, without handling DIY infrastructure, cost management, scaling, and other headaches.
This is simple implementation of MaskTrack_Box only requiring a bounding box for video object segmentation.
MIM Installs OpenMMLab Packages
OpenMMLab Image Classification Toolbox and Benchmark
OpenMMLab Computer Vision Foundation
OpenMMLab Model Deployment Framework
OpenMMLab Detection Toolbox and Benchmark
OpenMMLab Image and Video Editing Toolbox
OpenMMLab Foundational Library for Training Deep Learning Models
OpenMMLab Rotated Object Detection Toolbox and Benchmark
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
OpenMMLab Self-Supervised Learning Toolbox and Benchmark
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.