Stars
An open-source RAG-based tool for chatting with your documents.
A database of 650 Machine Learning (ML) system design case studies from 100+ companies.
Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"
Implementing Deep Convolutional Neural Network in C without External Libraries for YUV video Super-Resolution
Cross-platform, customizable ML solutions for live and streaming media.
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Optical Flow Prediction with TensorFlow. Implements "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume," by Deqing Sun et al. (CVPR 2018)
Convolution NN resize initialization for subpixel convolutions
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
RetinaFace (Single-stage Dense Face Localisation in the Wild, 2019) implemented (ResNet50, MobileNetV2 trained on single GPU) in Tensorflow 2.0+. This is an unofficial implementation. With Colab.
A curated list of practical financial machine learning tools and applications.
Image augmentation for machine learning experiments.
A collection of AWESOME things about domain adaptation
Diem’s mission is to build a trusted and innovative financial network that empowers people and businesses around the world.
Encode RGBA/YUV images to VP8 buffer with WebRTC streaming
Keras implementation of Deeplab v3+ with pretrained weights
DeepLabv3+ built in TensorFlow
Sarasra / models
Forked from tensorflow/modelsModels and examples built with TensorFlow
Build cross-platform desktop apps with JavaScript, HTML, and CSS
Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling serv…
LevelDB is a fast key-value storage library written at Google that provides an ordered mapping from string keys to string values.
State-of-the-art 2D and 3D Face Analysis Project