機械学習 · GitHub

A neural network training framework within a task-based parallel programming paradigm

NNtrainer is Software Framework for Training and Inferencing Neural Network Models on Devices.

• Run Locally, Fully Offline — Training and inference on edge devices with zero cloud dependency. Data stays on the device.
• On-Device Training & Personalization — Fine-tune models on-device with private user data. Supports Transfer Learning, Few-Shot Learning, and Continuous Learning.

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

High quality in silico spectral library generation for data-independent acquisition proteomics

中文语音识别; Mandarin Automatic Speech Recognition;

AMD-SHARK Studio -- Web UI for SHARK+IREE High Performance Machine Learning Distribution

Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline

Object Tracking in Tensorflow ( Localization Detection Classification ) developed to partecipate to ImageNET VID competition

A library created to revitalize C++ as a machine learning front end. Per aspera ad astra.

Deep survival analysis made easy

A Python toolkit for Reservoir Computing and Echo State Network experimentation based on pyTorch. EchoTorch is the only Python module available to easily create Deep Reservoir Computing models.

A free, open source, and privacy-focused browser extension to block “not safe for work” content built using TensorFlow.js.

Python programming assignments for Machine Learning by Prof. Andrew Ng in Coursera

NucliaDB, The AI Search database for RAG

• Store text, files, vectors, labels and annotations
• Perform text searches and given a word or set of words, return resources in our database that contain them.

SeqSeg (Sequential Vessel Segmentation)

Ensembling Off-the-shelf Models for GAN Training (CVPR 2022 Oral)