[ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
- bev
- end-to-end
- real-time
- transformer
89,572 visible repositories in the index
9,049–9,072 of 15,401 · Most stars
[ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
An official Qdrant Model Context Protocol (MCP) server implementation
WFB-NG - the next generation of long-range packet radio link based on raw WiFi radio
Countdown timer and stopwatch in your terminal
🔐 Lockdoor Framework : A Penetration Testing framework with Cyber Security Resources
FastAPI-Amis-Admin is a high-performance, efficient and easily extensible FastAPI admin framework. Inspired by django-admin, and has as many powerful functions as django-admin.
💬 An extensive collection of exceptional resources dedicated to the captivating world of talking face synthesis! ⭐ If you find this repo useful, please give it a star! 🤩
Noise2Noise: Learning Image Restoration without Clean Data - Official TensorFlow implementation of the ICML 2018 paper
TaoSync是一个适用于OpenList v3+的自动化同步工具/Sync for OpenList/AList
E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can connect to any LLM for secure computer use.
Dynamic and elegant desktop setup inspired by Material You, featuring auto-generated colors, fluid animations, and customizable user experience.
Askbot is a Django/Python Q&A forum. **Contributors README**: https://github.com/ASKBOT/askbot-devel#how-to-contribute. Commercial hosting of Askbot and support are available at https://askbot.com
Implementation of Non-local Block.
HomeTube is a friendly video downloader managing single video URL into organized content structure for automatic home media server experience.
🦠 A simple and fast (< 200ms) API for tracking the global coronavirus (COVID-19, SARS-CoV-2) outbreak. It's written in python using the 🔥 FastAPI framework. Supports multiple sources!
A Sublime Text Plugin for Arduino
SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.
First AI Journey for DevOps - with comprehensive learning paths, practical tips, and enterprise guidelines
Native Multimodal Models are World Learners
Dual LSTM Encoder for Dialog Response Generation
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
Python wrapper for the arXiv API
Libraries and examples to support Pimoroni Pico add-ons in C++ and MicroPython.
Open-source implementation of Google Vizier for hyper parameters tuning