An open-source implementaion for fine-tuning Qwen2-VL and Qwen2.5-VL series by Alibaba Cloud.

Build AI Assistants with memory, knowledge and tools.

《开源大模型食用指南》基于AutoDL快速部署开源大模型，更适合中国宝宝的部署教程

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

基于Pytorch的OCR工具库，支持常用的文字检测和识别算法

交通领域的大模型

一些关于目标检测的脚本的改进思路代码，详细请看readme.md

商用级开源语音自动识别程序库，开箱即用，全平台支持，中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide a set of easier APIs to call ASR models.

Python - 100天从新手到大师

PyTorch implementation of BMVC2022 paper Masked Vision-Language Transformers for Scene Text Recognition

🔥🔥🔥YOLOv5, YOLOv6, YOLOv7, PPYOLOE, YOLOX, YOLOR, YOLOv4, YOLOv3, PPYOLO, PPYOLOv2, Transformer, Attention, TOOD and Improved-YOLOv5-YOLOv7... Support to improve backbone, neck, head, loss, IoU, NM…

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

MobileFaceSwap: A Lightweight Framework for Video Face Swapping (AAAI 2022)

这里面存放了一些目标检测算法的数据增强方法。如mosaic、mixup。

3D点云数据配准 SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration (CVPR 2022)

基于Pytorch实现的声音分类

语音信号处理试验教程，Python代码

🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

植物识别 (Plant Recognition)

http://www.facegood.cc

Repository for MeshTalk supplemental material and code once the (already approved) 16 GHS captures our lab will make publicly available are released.

音视频流媒体权威资料整理，500+份文章，论文，视频，实践项目，协议，业界大神名单。

A real-time version of FCOS, inspired by FCOSv2.