Haian Huang(深度眸)

mmdetection最小学习版

多模态 MM +Chat 合集

yolov5的注释版本

Code segment are often used in deep learning algorithms(pytorch/numpy)

OpenMMLab Detection Toolbox and Benchmark

mini dataloader

Python资源大全中文版，内容包括：Web框架、网络爬虫、网络内容提取、模板引擎、数据库、数据可视化、图片处理、文本处理、自然语言处理、机器学习、日志、代码分析等

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为15个章节，近20万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06

自动监控开源项目 PR 动态

XTuner is a toolkit for efficiently fine-tuning LLM

OpenMMLab YOLO series toolbox and benchmark

u2net

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

A technical report on convolution arithmetic in the context of deep learning

Code release for our CVPR 2023 paper "Detecting Everything in the Open World: Towards Universal Object Detection".

GatedDeltaNet implementation with variable length sequence support

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Example models using DeepSpeed

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks

The official Meta Llama 3 GitHub site

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Reformatted Alignment

Grounded Language-Image Pre-training

A paper list of object detection using deep learning.

Flickr30K Entities Dataset

Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.

The classical papers and codes about generative adversarial nets

OpenCV问答群1,QQ群号:187436093

python notes

A lightweight framework for building LLM-based agents

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

AReaL inference pipeline example - AI generated demo

verl: Volcano Engine Reinforcement Learning for LLMs

SGLang is a fast serving framework for large language models and vision language models.

A Scientific Multimodal Foundation Model

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, InternVL3, Ovis2.5, Llava, GLM4v, Phi4, ...) (AAAI 2025).

slime is a LLM post-training framework aiming at scaling RL.

Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs

A native PyTorch Library for large model training

Aligning and Prompting Everything All at Once for Universal Visual Perception

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Efficient Triton Kernels for LLM Training

Janus-Series: Unified Multimodal Understanding and Generation Models

Train transformer language models with reinforcement learning.

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

Ring attention implementation with flash attention

A GPipe implementation in PyTorch

No description.

No description.

Accelerating the development of large multimodal models (LMMs) with lmms-eval

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

Implementing a ChatGPT-like LLM from scratch, step by step

Visual Instruction Tuning: Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.

No description.

LAVIS - A One-stop Library for Language-Vision Intelligence

GLEE: General Object Foundation Model for Images and Videos at Scale

Recent LLM-based CV and related works. Welcome to comment/contribute!

Official PyTorch implementation of "Multi-modal Queried Object Detection in the Wild" (accepted by NeurIPS 2023)

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

[CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and language

InternLM has open-sourced a 7 and 20 billion parameter base models and chat models tailored for practical scenarios and the training system.

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

official rtdetr, official rt-detr, rtdetr, rt-detr, Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection

This is the pytorch implement of our paper "RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model"

No description.

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

No description.

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and other exciting features.

No description.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

StableLM: Stability AI Language Models

Marrying Grounding DINO with Segment Anything !

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

A new framework for open-vocabulary object detection, based on maskrcnn-benchmark

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite

OpenMMLab Foundational Library for Training Deep Learning Models

OpenMMLab course index and materials

No description.

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

No description.

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Animation engine for explanatory math videos

Code release for ConvNeXt model

MMDeploy is an open-source deep learning model deployment toolset

No description.

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

OpenMMLab FewShot Learning Toolbox and Benchmark

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

YOLOX is a high-performance anchor-free YOLO. Exceeding yolov3~v5 with ONNX, TensorRT, ncnn, and Openvino supported.

OpenMMLab Computer Vision Foundation

OpenMMLab Pose Estimation Toolbox and Benchmark.

RTMP 推流器，RTMP(HLS)秒开播放器，跨平台（Win,IOS,Android）开源代码

fast image augmentation library and easy to use wrapper around other libraries

Cool Python features for machine learning that I used to be too afraid to use

Git repository for the "Python Language Features and Tricks You May Not Know Article" at http://sahandsaba.com/thirty-python-language-features-and-tricks-you-may-not-know.html

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Various examples for Kotlin

Papers and Benchmarks about semantic segmentation, instance segmentation, panoptic segmentation and video segmentation

A new implement of RecyclerView with HeaderViews

Data Augmentation For Object Detection

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

gank.io unofficial client, RxJava & Retrofit

Most popular metrics used to evaluate object detection algorithms

My own leetcode all solutions by python

A resource repository for 3D machine learning

:pencil2: Neural Style Transfer: A Review

OReilly Hands On Machine Learning with Scikit Learn and TensorFlow (Sklearn与TensorFlow机器学习实用指南)

Artificial Intelligence projects, documentation and code.

Models and examples built with TensorFlow

《21个项目玩转深度学习———基于TensorFlow的实践详解》配套代码

A curated list of object proposals resources for object detection

致力于将李航博士《统计学习方法》一书中所有算法实现一遍

No description.

Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.

Keras/Tensorflow implementation of our paper Grayscale Image Colorization using deep CNN and Inception-ResNet-v2 (https://arxiv.org/abs/1712.03400)

Lviv Data Science Summer School 2016 project

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

Machine Learning、Deep Learning、PostgreSQL、Distributed System、Node.Js、Golang

来疯直播安卓控件，支持flv，支持rtmp，支持添加视频特效等等

一个仿今日头条的开源项目

颜值控，搜罗各种需求，不断完善

This project is a SDK about video stream live

Simple-Rtmp-Server win32 builds

No description.

librtmp for Android and iOS

android rtmp push sdk

scikit-learn: machine learning in Python

No description.

A custom CheckBox with animation for Android.