HazeSpace2M is a large scale paired hazy dataset for training and evaluating haze type classification models and single image dehazing models.

深度学习经典、新论文逐段精读

Collection of popular and reproducible image denoising works.

The Meson Build System

Play time!

Inno Setup is an open-source installation builder for Windows applications by Jordan Russell and Martijn Laan. Since its introduction in 1997, Inno Setup has been trusted by developers and organiza…

ONNX Script editor & visualiser running completely in the browser thanks to Pyodide and Netron

This repo has been migrated to https://code.larus.se/lmas/opensimplex

Video datasets

ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

CUDA Python: Performance meets Productivity

The ultimate Python binding for Vulkan API

Image Signal Processor

A curated list of references for MLOps

This is a resouce list for low light image enhancement

An Open Framework for Federated Learning.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

PyTorch Neural Network eXchange

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Simple framework for image and video deblurring, implemented by PyTorch

A python library for self-supervised learning on images.

Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT).

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Automated deep learning algorithms implemented in PyTorch.

Pytorch implementation of Shift-Net: Image Inpainting via Deep Feature Rearrangement (ECCV, 2018)