Aprendizaje automático · GitHub

On-device subject cutouts, image labels, and OCR for React Native. Apple Vision (iOS) · Google ML Kit (Android). Built with Nitro Modules.

• removeBackground Subject cutout — trim, export PNG/JPEG, optional mask classifyImage Ranked labels — offline on both platforms readText OCR — Latin / CJK / Devanagari on Android; Vision on iOS 18+ analyzeImage All three from a single decode Cutout and OCR results live on the native side until you export them. Call dispose() when done.
• supportsBackgroundRemoval - Cutouts available

The BiLSTM-CRF model implementation in Tensorflow, for sequence labeling tasks.

The vehicle orientation dataset is a large-scale dataset containing more than one million annotations for vehicle detection with simultaneous orientation classification using a standard object detection network.

Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包，支持亿级数据文搜文、文搜图、图搜图，python3开发，开箱即用。

基于Pytorch和torchtext的自然语言处理深度学习框架。

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

An Open-Source Package for Textual Adversarial Attack.

DeepDEM: Digital Elevation Model refinement using deep learning

Open-source modular autonomous driving simulation platform with computer vision, deep learning, and sensor fusion. Features lane detection, object recognition, various safety features, and adaptive control in BeamNG.tech, with real-time visualization via Foxglove.

Оптимизация долгосрочного портфеля акций

Revisiting Pre-trained Models for Chinese Natural Language Processing (MacBERT)