Book4_Power-of-Matrix
Visualize-ML
10,170星标+324小时
Book_4_《矩阵力量》 | 鸢尾花书：从加减乘除到机器学习；上架！
机器学习 · GitHub
发现模型训练、评估与推理框架，比较深度学习和机器学习项目的社区关注度。
实用 GitHub 项目
4,743 个项目
arl-eegmodels
vlawhern
1,591星标+324小时
This is the Army Research Laboratory (ARL) EEGModels Project: A Collection of Convolutional Neural Network (CNN) models for EEG signal classification, using Keras and Tensorflow
volcano
volcano-sh
6,084星标+324小时
云原生批处理系统（CNCF 项目）
wespeaker
wenet-e2e
1,467星标+324小时
Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
aimbuddy
1337Xcode
85星标+224小时
A fully on‑device Android‑native aim assistant
NamiGPT
aa1143
218星标+224小时
零基础入门大模型（LLM）的基础教程：从零手写 GPT-2，一行行看懂大模型是怎么工作的 | Build GPT-2 from scratch in PyTorch, step by step
stable-diffusion-webui-docker
AbdBarho
7,302星标+224小时
Easy Docker setup for Stable Diffusion with user-friendly UI
awesome-datascience
academic
30,319星标+224小时
:memo: 一个出色的数据科学资源库，助你学习数据科学并将其应用于现实问题。
RAVE
acids-ircam
1,831星标+224小时
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
lama
advimman
10,381星标+224小时
🦙 LaMa 图像修复：基于傅里叶卷积的分辨率鲁棒大掩码图像修复，WACV 2022
stanford-cs-229-machine-learning
afshinea
20,378星标+224小时
斯坦福大学 CS 229《机器学习》VIP 速查表
stanford-cs-230-deep-learning
afshinea
7,138星标+224小时
VIP cheatsheets for Stanford's CS 230 Deep Learning
ComfyUI_VNCCS
AHEKOT
1,763星标+224小时
Visual Novel Character Creation Suite is a comprehensive tool for creating character sprites for visual novels. It allows you to create unique characters with a consistent appearance across all images, which was previously a challenging task when using neural networks.
NN-SVG
alexlenail
5,701星标+224小时
可直接用于发表的神经网络架构示意图。
torchcurves
alexshtf
72星标+224小时
Parametric differentiable curves with PyTorch for continuous embeddings, shape-restricted models, or KANs
- Differentiable: Custom autograd function ensures gradients flow properly through the curve evaluation.
- Vectorized: Vectorized operations for efficient batch and multi-curve evaluation.
Olmo-core
allenai
1,792星标+224小时
PyTorch building blocks for the OLMo ecosystem
AI-Expert-Roadmap
AMAI-GmbH
31,356星标+224小时
2022 年成为人工智能专家的路线图
22,958星标+224小时
CVPR 2026 论文和开源项目合集
MLQuestions
andrewekhalel
4,965星标+224小时
Machine Learning and Computer Vision Engineer - Technical Interview Questions
- Ridge (L2 norm)
- Oversampling or undersampling. Instead of sampling with a uniform distribution from the training dataset, we can use other distributions so the model sees a more balanced dataset.
fast-plate-ocr
ankandrew
812星标+224小时
Lightweight & fast OCR models for license plate text recognition.
- Keras 3 Backend Support: Train seamlessly using TensorFlow, JAX, or PyTorch backends 🧠
- Efficient Execution: Lightweight models that are cheap to run 💰
voxlock
arbazsiddiqui
110星标+224小时
The best performing voice isolator there is. Keeps the caller's voice and removes the other voices in the room before speech-to-text hears them. Open source, streaming, runs on CPU and in the browser. pip install voxlock
rosnav-rl
Arena-Rosnav
106星标+224小时
Modular DRL framework for autonomous robot navigation in ROS2. Plug-and-play RL backends (Stable-Baselines3, DreamerV3), composable reward functions, observation spaces & neural architectures - built for research and deployment.
- Wrap any RL backend - the common RL_Model interface means you swap SB3 ↔ DreamerV3 ↔ your own implementation without touching training code. Same observations, same reward, same config.
- Declarative data pipeline - define collectors by ROS message type (sensor_msgs/LaserScan); preprocessing and topic wiring happen automatically.
AI-Study-Group
ArturoNereu
1,388星标+224小时
Resources to learn AI
- Standard Notations for Deep Learning
- AI Index Report | Stanford
pytorch
Ascend
607星标+224小时
As the core component of the Ascend for PyTorch community, TorchNPU is a deep learning adapter plugin built by Ascend for PyTorch, enabling the PyTorch framework to directly invoke Ascend NPU and providing developers with the powerful compute capabilities of Ascend AI processors. (About Ascend NPU: Ascend NPU (Neural Processing Unit) is a series of
- Basic Compute: Extensive support for PyTorch native APIs and custom APIs, covering mainstream AI scenarios with a consistent experience, enabling rapid model and algorithm implementation.
- Distributed: Supports accelerating distributed training via FSDP2. Core compute APIs support DTensor, along with collective communication primitives such as AllGather, AllReduce, and AllToAll, as well as point-to-point primitives like Send and Recv.