gravitychen
Follow
CV-DL
[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
[CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+
ncnn is a high-performance neural network inference framework optimized for the mobile platform
PyTorch dataset extended with map, cache etc. (tensorflow.data like)
Fast Fourier Color Constancy: an auto white balance solution with machine learning in Fourier space
Color Constancy by Reweighting Image Feature Maps
Official code of the "Rendering Nighttime Image Via Cascaded Color and Brightness Compensation"
Seeing Motion in the Dark. ICCV19
LightPipes for Python, "Pure Python version"
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.
A simple tutorial to use Visdom to plot your PyTorch training graphs
Reference github repository for the paper "Defocus Deblurring Using Dual-Pixel Data". We introduce a deep neural network (DNN) architecture that uses the dual-pixel (DP) sub-aperture views to reduc…
🎨 Diagram as Code for prototyping cloud system architectures
Curated list of awesome colour science resources 😎
FFCV: Fast Forward Computer Vision (and other ML workloads!)
Source code for 2021 CVPR paper "Seeing in Extra Darkness Using a Deep-red Flash"
Visualizer for neural network, deep learning and machine learning models
learning materials for PyTorch beginners
A light-weight script for maintaining a LOT of machine learning experiments.
GUI-based software for training, evaluating and applying deep neural nets for image classification
alfred-py: A deep learning utility library for **human**, more detail about the usage of lib to: https://zhuanlan.zhihu.com/p/341446046
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
LightSeq: A High Performance Library for Sequence Processing and Generation