機械学習 · GitHub

A tool for quantitative risk analysis of Android applications based on machine learning techniques

PyTorch Implementation for Deep Metric Learning Pipelines

MLOps Workshop using Weights and Bias (Wandb) and Github Actions.

LLM algorithm practice lab with theory, solutions, and test cases.《大模型算法与系统教程》面向大模型入门到进阶的算法实战教程，覆盖原理讲解、答案解析、测试用例与 CUDA/Triton 实战。

• Notebook-first: Each lesson is organized around runnable code, exercises, answer cells, and basic validation.
• Goal-oriented entry: Start from Part 02 for implementation practice, or follow the architecture, post-training, inference, performance, and operator routes.

A 3D Slicer extension to use AMASSS, ALI-CBCT and ALI-IOS

• Simple: Perform time consuming task with a few clicks.
• Automatic: Automate important Dental and Cranio Facial analysis tasks.

Baobab is an open source multi-tenant web application designed to facilitate the application and selection process for large scale meetings within the machine learning and artificial intelligence communities globally. Supported by the Deep Learning Indaba

Production-ready visual anomaly detection from normal images, featuring PaDiM, ultra-light PatchCore, automated edge deployment, and optimized ONNX, OpenVINO, TensorRT INT8, Hailo, and KV260 support.

本项目实现了一种基于 VAE-CycleGAN 的图像重建无监督缺陷检测算法。该算法结合了变分自编码器 (VAE) 和 CycleGAN 的优势，无需标注数据即可检测图像中的缺陷/异常。This project implements an unsupervised defect detection algorithm for image reconstruction based on VAE-CycleGAN. This algorithm combines the advantages of variational autoencoders (VAE) and CycleGAN to detect defects in images without any supervision.

• Unsupervised learning: No need for labeled anomaly data
• VAE-based image reconstruction

AAAI 2024 Papers: Explore a comprehensive collection of innovative research papers presented at one of the premier artificial intelligence conferences. Seamlessly integrate code implementations for better understanding. ⭐ experience the forefront of progress in artificial intelligence with this repository!

基于u-net，cv2以及cnn的中文车牌定位，矫正和端到端识别软件，其中unet和cv2用于车牌定位和矫正，cnn进行车牌识别，unet和cnn都是基于tensorflow的keras实现

Ứng dụng đọc tiếng Việt cho Windows/macOS/Linux, Web, Android, iOS Simulator và Chrome Extension: tải về chạy ngay, model có sẵn, đọc văn bản dài, xuất WAV. Mã nguồn mở; model nghiên cứu phi thương mại.

Anchor-Align (arXiv:2607.13429): VLA finetuning that prevents behavior cloning from erasing pretrained VLM representations (catastrophic forgetting) and aligns language with actions. OOD generalization on a physical xArm7, LIBERO-PRO, LIBERO-Plus and CALVIN.

Anchor: A universal, hardware-accelerated CLI tool for subtitle synchronization (Whisper) and context-aware translation (NLLB)

A GPU-accelerated library for Tree-based Genetic Programming, leveraging PyTorch and custom CUDA kernels for high-performance evolutionary computation. It supports symbolic regression, classification, and policy optimization with advanced features like multi-output trees and benchmark tools.

• Leverage specialized CUDA kernels to optimize critical TGP operations.
• Enhance computational efficiency, especially for large populations, enabling faster execution compared to traditional TGP methods.

Streamlit dashboard for stock charts, technical indicators and an experimental Random Forest forecast

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

PyTorch code and models for VJEPA2 self-supervised learning from video.