jiangziben

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

fine-tune-train_segment_anything_2_in_60_lines_of_code

The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)

segment-anything-2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

recognize-anything

Open-source and strong foundation image recognition models.

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Bunny

A family of lightweight multimodal models.

LLaVA-NeXT

Grounded-SAM-2

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO and SAM 2

Deformable-DETR

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

TAPTR

[ECCV 2024] Official implementation of the paper "TAPTR: Tracking Any Point with Transformers as Detection"

Semantic-SAM

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

co-tracker

CoTracker is a model for tracking any point (pixel) on a video.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

anylabeling

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!

SAM-6D

[CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Mask2Former

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

OpenScene

3D Occupancy Prediction Benchmark in Autonomous Driving

ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

bevfusion

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

fastdup

fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data operations costs at an unparalleled scale.

LLM101n

LLM101n: Let's build a Storyteller

Eureka

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

objectdetection_script

一些关于目标检测的脚本的改进思路代码，详细请看readme.md

pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

CameraLaserCalibrate

Camera Laser Calibrate python version

cvat

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

universal_manipulation_interface

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

umi-on-legs

UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers