机器学习 · GitHub

🔥[IEEE TPAMI 2020] Deep Learning for 3D Point Clouds: A Survey

Python hands on tutorial with 50+ Python Application (10 lines of code) By @xiaowuc2

Pytorch implementation of "Fully-Convolutional Siamese Networks for Object Tracking"

Reconstruct Watertight Meshes from Point Clouds [SIGGRAPH 2020]

For automating the creation of large batches of AI-generated artwork locally.

Julia package for automated Bayesian inference on a factor graph with reactive message passing

Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

使用深度神经网络自动进行图像着色。《Colorful Image Colorization》。发表于 ECCV 2016。

MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.

• LaTeX Formula Recognition: Accurately recognizes complex LaTeX mathematical formulas, ensuring mathematical expression accuracy.
• Table Recognition: Efficiently processes and recognizes various tables, generating corresponding LaTeX table code.

BOT-MMORPG-AI is your personal gaming assistant that uses artificial intelligence to play your favorite MMORPG and RPG games automatically. It watches how YOU play, learns from your gameplay, and then takes over the boring, repetitive tasks while you relax, work, or sleep.

• ✅ Auto-Farming: Collect resources automatically while you're away
• ✅ Smart Navigation: Travel from point A to point B without getting stuck

A blazing-fast, memory-safe neural network library for Rust that brings the power of FANN to the modern world.

• Default features - Enable model I/O, serialization, compression, logging, and parallel-related utilities. CPU inference does not require a GPU.
• io - Enables file formats and training-data I/O. Keep bounds on bytes, decompressed data, and declared model dimensions when loading external data.

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