wenkai's repositories
anylabeling
Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything, MobileSAM!!
autodistill
Images to inference with no labeling (use foundation models to train supervised models)
BiSCI
A Toolbox for Binarized Spectral Compressive Imaging (NeurIPS 2023)
CYWS-3D
The official implementation of the paper The Change You Want to See (Now in 3D) (ICCVW 2023).
DiAD
Official implementation of DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection.
fiftyone
The open-source tool for building high-quality datasets and computer vision models
Grounded-Segment-Anything
Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP & Whisper - Automatically Detect , Segment and Generate Anything with Image, Text, and Speech Inputs
kornia
Geometric Computer Vision Library for AI
leedl-tutorial
《李宏毅深度学习教程》，PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
LoFTR
Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021
loguru
Python logging made (stupidly) simple
matplotplusplus
Matplot++: A C++ Graphics Library for Data Visualization 📊🗾
mmdeploy
OpenMMLab Model Deployment Framework
Myriad
Open-sourced codes, IAD vision-language datasets and pre-trained checkpoints for Myriad.
nanodet
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
nuclio
High-Performance Serverless event and data processing platform
onnx-simplifier
Simplify your onnx model
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
redis-plus-plus
Redis client written in C++
smallchat
A minimal programming example for a chat server
stable-diffusion-webui
Stable Diffusion web UI
SuperPoint-SuperGlue-TensorRT
SuperPoint and SuperGlue with TensorRT.
TensorRT
NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.
TensorRT-Alpha
🔥🔥🔥TensorRT-Alpha supports YOLOv8、YOLOv7、YOLOv6、YOLOv5、YOLOv4、v3、YOLOX、YOLOR...🚀🚀🚀CUDA IS ALL YOU NEED.🍎🍎🍎It also supports end2end CUDA C acceleration and multi-batch inference.
Tensorrt-Deformable-Detr
Tensorrt-Deformable-Detr
ultralytics
NEW - YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
YOLOv8-TensorRT
YOLOv8 using TensorRT accelerate !