🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).

Effortless data labeling with AI support from Segment Anything and other awesome models.

An open-source tool-augmented conversational language model from Fudan University

Ultralytics YOLO11 🚀

yolov7 face detection with landmark

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

基于retinaface人脸检测和facenet人脸识别的Flask服务

Convolutional recurrent network in pytorch

Implementation of popular deep learning networks with TensorRT network definition API

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

An annotated implementation of the Transformer paper.

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

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

Scaled-YOLOv4: Scaling Cross Stage Partial Network

Convolutional Neural Networks

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

CVPR 2025 论文和开源项目合集

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)

开源图像标注工具(支持人脸关键点/不规则四边形/多边形标注)

SAPD (Soft Anchor-Point Object Detection) implementation in Keras and Tensorflow

Google Brain AutoML

NGINX-based Media Streaming Server

OpenMMLab Detection Toolbox and Benchmark

notepad