simonJJJ

llama.cpp

Port of Facebook's LLaMA model in C/C++

ggml

Tensor library for machine learning

AdelaiDet

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

bdd100k

BDD100K Dataset - CVPR 2020 Oral Paper

Deformable-DETR

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

detr

End-to-End Object Detection with Transformers

Elevater_Toolkit_IC

Toolkit for Elevater Benchmark

InstanceAnalyzer

DARC

Decentralized Autonomous Regulated Company (DARC), a company virtual machine that runs on any EVM-compatible blockchain, with on-chain law system, multi-level tokens and dividends mechanism.

flash-attention

Fast and memory-efficient exact attention

iopath

A python library that provides common I/O interface across different storage backends.

leveldb

LevelDB is a fast key-value storage library written at Google that provides an ordered mapping from string keys to string values.

membership-inference

Code for Membership Inference Attack against Machine Learning Models (in Oakland 2017)

mmdetection

Open MMLab Detection Toolbox and Benchmark

mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

models

Models and examples built with TensorFlow

OFA

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

ORB_SLAM3

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

PaddleDetection

Object detection and instance segmentation toolkit based on PaddlePaddle.

pegbis

Python implementation of "Efficient Graph-Based Image Segmentation" paper

QueryInst

Instances as Queries (https://arxiv.org/abs/2105.01928)

SA-SSD

Scene-Graph-Benchmark.pytorch

A new codebase of Scene Graph Generation based on maskrcnn-benchmark. A Pytorch implementation of the CVPR 2020 Oral paper "Unbiased Scene Graph Generation from Biased Training"

SEED-Bench

A benchmark for evaluating Multimodal LLMs using multiple-choice questions.

SparseR-CNN

End-to-End Object Detection with Learnable Proposal

training

Reference implementations of training benchmarks

vision

Datasets, Transforms and Models specific to Computer Vision

YOLOP

You Only Look Once for panopitic driving perception.（https://arxiv.org/abs/2108.11250）