Stars
HE-Drive: Human-Like End-to-End Driving with Vision Language Models
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
Our insights of Openpilot, a deepdive project on it
Sample codes for my CUDA programming book
基于 Asp.Net Core 9.0、Uni-App开发，支持可视化布局的小程序商城系统，前后端分离，支持分布式部署，跨平台运行，拥有分销、代理、团购、拼团、秒杀、直播、优惠券、自定义表单等众多营销功能，拥有完整SKU、下单、售后、物流流程。支持一套代码编译发布微信小程序版、H5版、Android版、iOS版、支付宝小程序版、字节跳动小程序版、QQ小程序版等共10个平台。
使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
Printed and handwritten text segmentation using fully convolutional networks and CRF post-processing
StyleFlow: Attribute-conditioned Exploration of StyleGAN-generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)
Official tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”
基于caffe的LSTM OCR案例，能够利用该案例完成序列的识别，包括验证码、车牌、身份证号码、地址等长序列动长的内容识别
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别
简单车牌识别-Mask_RCNN定位车牌+手写方法分割字符+CNN单个字符识别
💻深度学习实战：手写数字识别、Discuz验证码识别、垃圾分类、语义分割
A library of reinforcement learning components and agents
Pre-trained Deep Learning models and demos (high quality and extremely fast)