機械学習 · GitHub

ONNXim is a fast cycle-level simulator that can model multi-core NPUs for DNN inference

Official PyTorch implementation of VisionHOPE: Visual Backbones as Self-Modifying Learning Systems.

Code and information for face image quality assessment with SER-FIQ

[参赛队伍] TAAC 2026 腾讯广告算法大赛 X KDD 2026

PyC (Pytorch Concepts) is a PyTorch-based library for designing concept-based interpretable deep learning models.

Submission to https://pytorch.org/hub/

Blazing fast framework for fine-tuning similarity learning models

• 🌀 Warp-speed fast: With the built-in caching mechanism, Quaterion enables you to train thousands of epochs with huge batch sizes even on laptop GPU.
• 🐈‍ Small data compatible: Pre-trained models with specially designed head layers allow you to benefit even from a dataset you can label in one day.

[CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration

数学建模和机器学习/深度学习/大模型的笔记和资料（持续更新中......）。

Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes (CVPR2022)

CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild (CVPR2022)

PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features

QuPath - Open-source bioimage analysis for research

オープンソースの SenseVoiceSmall モデルです。中国語（普通話）、広東語、英語、日本語、韓国語の音声認識、言語識別、感情認識、音声イベント検出に対応しています。

• Research scope vs released checkpoint: The broader SenseVoice work reports training on more than 400,000 hours and support for more than 50 languages. The released SenseVoiceSmall checkpoint linked above supports Mandarin, Cantonese, English, Japanese, and Korean; the benchmark comparisons below are task- and language-specific.
• Possess excellent emotion recognition capabilities, achieving and surpassing the effectiveness of the current best emotion recognition models on test data.

Residual networks implementation using Keras-1.0 functional API

Build a World Model from Scratch — the Vizuara AI lecture series: slides, from-scratch code, and Colab notebooks

AESTETIK: Convolutional autoencoder for learning spot representations from spatial transcriptomics and morphology data