从 65,726 个高星开源项目里，
找到你要的下一个。

stanford-tensorflow-tutorials 是用 Python 编写的学习资料，用于系统学习与查阅。

This repository contains code examples for the Stanford's course: TensorFlow for Deep Learning Research.

lama 是用 Jupyter Notebook 编写的 AI 工具，用于人工智能方向的建模与推理。

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

techniques 是一个 AI 工具，用于人工智能方向的建模与推理。

Techniques for deep learning with satellite & aerial imagery

TTS 是用 Jupyter Notebook 编写的学习资料，用于系统学习与查阅。

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

PySyft 是用 Python 编写的学习资料，用于系统学习与查阅。

Perform data science on data that remains in someone else's server

pyod 是用 Python 编写的学习资料，用于系统学习与查阅。

A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orc…

espnet 是用 Python 编写的学习资料，用于系统学习与查阅。

End-to-End Speech Processing Toolkit

sonnet 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

TensorFlow-based neural network library

computervision-recipes 是用 Jupyter Notebook 编写的 AI 工具，用于人工智能方向的建模与推理。

Best Practices, code samples, and documentation for Computer Vision.

U-2-Net 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

neural-doodle 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to ano…

models 是用 Jupyter Notebook 编写的学习资料，用于系统学习与查阅。

A collection of pre-trained, state-of-the-art models in the ONNX format

AIMLInterviews 是用 Jupyter Notebook 编写的学习资料，用于系统学习与查阅，主打功能完整。

A Comprehensive Guide for Generative AI, Agentic AI, Multimodal AI, Physical AI Interviews. Proven Formula for multiple FAANG offers and more

attention-is-all-you-need-pytorch 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

A PyTorch implementation of the Transformer model in "Attention is All You Need".

notebooks 是用 Jupyter Notebook 编写的 AI 工具，用于人工智能方向的建模与推理。

A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet …

einops 是用 Python 编写的学习资料，用于系统学习与查阅，主打功能完整、可扩展。

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (har…

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generati…

tflearn 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Deep learning library featuring a higher-level API for TensorFlow.

RobustVideoMatting 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

darts 是用 Python 编写的学习资料，用于系统学习与查阅，主打易用。

A python library for user-friendly forecasting and anomaly detection on time series.

Stock-Prediction-Models 是用 Jupyter Notebook 编写的学习资料，用于系统学习与查阅。

Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations

oneflow 是用 C++ 编写的 AI 工具，用于人工智能方向的建模与推理，主打易用、可伸缩。

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

FlexLLMGen 是用 Python 编写的学习资料，用于系统学习与查阅。

Running large language models on a single GPU for throughput-oriented scenarios.

awesome-project-ideas 是一个资源清单，按主题汇总同类优质资源。

Curated list of Machine Learning, NLP, Vision, Recommender Systems Project Ideas