Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.
- ai
- data
- embeddings
- etl
111,820 visible repositories in the index
4,225–4,248 of 5,481 · Most stars
Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.
代码 -《深度学习之PyTorch物体检测实战》
Python Computer Vision & Video Analytics Framework With Batteries Included
invisible playwright mcp: Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.
🔨 Geetest Crack | 从 JavaScript 层面一步步破解极验「鼠标点击+滑块滑动」各种加密参数
AlphaPose + ST-GCN + SORT.
Fast Automatic License Plate Recognition (ALPR) framework.
Enhanced version of Fooocus for SDXL, more suitable for Chinese and Cloud
Modern tactical exploitation toolkit.
[CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition
An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come
Robust evasion attacks against neural network to find adversarial examples
EVAL(Elastic Versatile Agent with Langchain) will execute all your requests. Just like an eval method!
Geometric Algebra for Python
Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios
体系化的机器人教学文档,涵盖数学基础、C++进阶、规划控制、SLAM等
Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
Speech Enhancement Generative Adversarial Network in TensorFlow
AISBench Benchmark is a model evaluation tool built on OpenCompass, compatible with OpenCompass’s configuration system, dataset structure, and model backend implementation, while extending support for service-based models.
Instagram marketing skills for Claude Code and Codex: captions, carousels, hooks, hashtag strategy, and a weekly plan. Draft, humanize, and publish via Publora. MIT. Content engineering by Creative Content Crafts.
:zap: A newly designed ultra lightweight anchor free target detection algorithm, weight only 250K parameters, reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler
Python3 interview prep cheatsheet and examples
Hypergraph Neural Networks (AAAI 2019)
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation