djord97

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

annlite

⚡ A fast embedded library for approximate nearest neighbor search

awesome-mojo

Awesome Mojo Programming Language

codon

A high-performance, zero-overhead, extensible Python compiler using LLVM

colour

Colour Science for Python

DAMO-YOLO

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

deepsparse

Inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application

einops

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

FLM

Accelerating Vision-Language Pretraining with Free Language Modeling (CVPR 2023)

gdown

Download a large file from Google Drive (curl/wget fails because of the security notice).

ImageBind

ImageBind One Embedding Space to Bind Them All

mmpose

OpenMMLab Pose Estimation Toolbox and Benchmark.

OC_SORT

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

OccDepth

Maybe the first academic open work on stereo 3D SSC method with vision-only input.

opencv-mobile

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly

openpifpaf

Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.

sparseml

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

TensorRT-For-YOLO-Series

tensorrt for yolo series (YOLOv8, YOLOv7, YOLOv6....), nms plugin support

threestudio

A unified framework for 3D content generation.

torch2trt

An easy to use PyTorch to TensorRT converter

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything and XMem.

ultralytics

YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite

vector

A high-performance observability data pipeline.

yolov5-face

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931)

YOLOv6

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

yolov7-face

yolov7 face detection with landmark

yolov7-face-tensorrt

yolov7-face tensorrt

yolov8-face

yolov8 face detection with landmark

yolov8_tracking

Real-time multi-object tracking and segmentation using YOLOv8

djord97