spacewalk01

llama.cpp

LLM inference in C/C++

Fooocus

Focus on prompting and generating

frigate

NVR with realtime local object detection for IP cameras

supervision

We write your reusable computer vision tools. 💜

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

ggml

Tensor library for machine learning

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

pytorch-cifar

95.47% on CIFAR10 with PyTorch

NN-SVG

Publication-ready NN-architecture schematics.

MobileSAM

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

FairMOT

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

anomalib

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

sam.cpp

nncf

Neural Network Compression Framework for enhanced OpenVINO™ inference

BoT-SORT

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

nanosam

A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT

labelCloud

A lightweight tool for labeling 3D bounding boxes in point clouds.

cuPCL

A project demonstrating how to use the libs of cuPCL.

InstructDiffusion

PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

segment-anything-cpp-wrapper

MS3D

Auto-labeling of point cloud sequences for 3D object detection using an ensemble of experts and temporal refinement

MV-Tractus

A simple tool to extract motion vectors from h264 encoded videos.

BoTSORT-cpp

C++ implementation of BoT-SORT MOT algorithm with Re-ID and Camera Motion Compensation

FastSam_Awsome_TensorRT

segment-anything-tensorrt

kaggle-feedback-english-language-learning-1st-place-solution

Feedback Prize - English Language Learning: 1st place solution code

pointcloud-utils

A toolbox for pointcloud processing, including: filter, bounding box extraction, ground segmentation, cluster. And implemented by different algorithms(some with pcl wrapper). c++17 supported

llama.cpp

Visual C++ port of Facebook's LLaMA model in C/C++

sam-cpp-vs

sam.cpp visual studio integration

Point-Clouds-3D-Perception

Using the KITTI dataset, we employed Open3D to visualize, downsample, segment with RANSAC, cluster via DBSCAN, create 3D bounding boxes, and perform surface reconstruction on point clouds.