Machine Learning · GitHub

Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

• Built-in models: Ready-to-use FHE-friendly models with a user interface that is equivalent to their the scikit-learn and XGBoost counterparts
• Customs models: Concrete ML supports models that can use quantization-aware training. These are developed by the user using PyTorch or keras/tensorflow and are imported into Concrete ML through ONNX

SFML is the first fully local AI solar forecast for Home Assistant, powered by a local Attention Transformer. No external AI — such as ChatGPT, Gemini, or Grok — required. Runs entirely on your device for complete privacy.

• The forecast - Hourly for 72 hours, learned from your roof: shading, local weather, panel groups — and forecast quality is measured, not claimed.
• Smart Charge - Charges the battery from the grid when electricity is cheap and the sun will not be enough — and leaves room for solar power otherwise.

Turn YouTube videos into deep learning resources with transcripts, bilingual translation, AI overviews, explanations, and notes. Bring your own keys.

MobileNet build with Tensorflow

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

Evaluation of Deep Learning Frameworks

An open-source book that helps readers quickly get started with deep learning development and research using PyTorch. All PyTorch tutorials in the book have been tested to ensure they run successfully.

Chess reinforcement learning by AlphaGo Zero methods.

基于Yolov5车牌检测,更快更准.

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photo tool. A lightweight AI algorithm for creating ID photos.

A tiny Transformer built from scratch in PyTorch, with an English-to-Chinese translation demo | 用 PyTorch 从零实现的小型 Transformer，附英译中演示，帮助理解模型原理

• One Python file: data processing, the model, training, and translation all live in transformer.py.
• Core components implemented by hand: scaled dot-product attention, multi-head attention, causal masking, and cross-attention.

使用机器学习算法完成对12306验证码的自动识别

[T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation

ResNeSt: Split-Attention Networks

The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)