1.rohitg00 / ai-engineering-from-scratch
Learn AI Engineering! Learn it. Build it. Ship it for others.
+13,353 stars
from 62,894 · score 9.50
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
48 repositories by Attention Score · Oct 4, 2026 – Nov 2, 2026 (UTC)
2.Oldcircle / geo-sleuth
An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.
+4,767 stars
from 503 · score 8.47
3.PSRben / VisionHOPE
Official PyTorch implementation of VisionHOPE: Visual Backbones as Self-Modifying Learning Systems.
+1,121 stars
from 244 · score 7.02
4.d2l-ai / d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
+932 stars
from 81,264 · score 6.84
5.ultralytics / ultralytics
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
+932 stars
from 62,086 · score 6.84
6.roboflow / supervision
We write your reusable computer vision tools. 💜
+435 stars
from 51,019 · score 6.08
7.kornia / kornia
🐍 Geometric Computer Vision Library for Spatial AI
+380 stars
from 11,396 · score 5.94
8.graphdeco-inria / gaussian-splatting
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
+336 stars
from 24,051 · score 5.82
9.d2l-ai / d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
+255 stars
from 29,727 · score 5.55
10.ultralytics / yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
+204 stars
from 58,043 · score 5.32
11.cvat-ai / cvat
CVAT is a leading data annotation platform for image, video, audio, and 3D datasets. It offers open-source, cloud, and enterprise products, as well as labeling services, with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.
+203 stars
from 16,841 · score 5.32
12.nerfstudio-project / nerfstudio
A collaboration friendly studio for NeRFs
+108 stars
from 12,031 · score 4.69
13.huggingface / datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
+92 stars
from 22,010 · score 4.53
14.alicevision / Meshroom
Node-based Visual Programming Toolbox
+78 stars
from 12,980 · score 4.37
15.mlfoundations / open_clip
An open source implementation of CLIP.
+72 stars
from 14,167 · score 4.29
16.wkentaro / labelme
Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.
+60 stars
from 16,191 · score 4.11
17.pytorch / vision
Datasets, Transforms and Models specific to Computer Vision
+59 stars
from 17,923 · score 4.09
18.autogluon / autogluon
Fast and Accurate ML in 3 Lines of Code
+56 stars
from 10,751 · score 4.04
19.qubvel-org / segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
+47 stars
from 11,744 · score 3.87
20.zalandoresearch / fashion-mnist
A MNIST-like fashion product database. Benchmark :point_down:
+43 stars
from 12,836 · score 3.78
21.lucidrains / vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
+41 stars
from 25,513 · score 3.74
22.scikit-image / scikit-image
Image processing in Python
+30 stars
from 6,599 · score 3.43
23.junyanz / pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
+27 stars
from 25,241 · score 3.33
24.jacobgil / pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
+25 stars
from 12,978 · score 3.26
25.ludwig-ai / ludwig
Low-code framework for building custom LLMs, neural networks, and other AI models
+25 stars
from 11,767 · score 3.26
26.ultralytics / yolov3
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
+21 stars
from 10,610 · score 3.09
27.lightly-ai / lightly
A python library for self-supervised learning and latent world models on images.
+10 stars
from 3,816 · score 2.40
28.STVIR / pysot
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
+9 stars
from 4,600 · score 2.30
29.visionml / pytracking
Visual tracking library based on PyTorch.
+8 stars
from 3,517 · score 2.20
30.davidsandberg / facenet
Face recognition using Tensorflow
+7 stars
from 14,352 · score 2.08
31.open-mmlab / mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
+7 stars
from 1,499 · score 2.08
32.JdeRobot / RoboticsAcademy
Learn Robotics with JdeRobot
+7 stars
from 500 · score 2.08
33.IBM / MAX-Image-Resolution-Enhancer
Upscale an image by a factor of 4, while generating photo-realistic details.
+6 stars
from 1,042 · score 1.95
34.SerpentAI / SerpentAIArchived
Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own!
+5 stars
from 6,984 · score 1.79
35.xinshuoweng / AB3DMOT
(IROS 2020, ECCVW 2020) Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics"
+5 stars
from 1,844 · score 1.79
36.QingyongHu / RandLA-Net
🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)
+5 stars
from 1,562 · score 1.79
37.richzhang / colorization
Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.
+4 stars
from 3,461 · score 1.61
38.astorfi / lip-reading-deeplearning
:unlock: Lip Reading - Cross Audio-Visual Recognition using 3D Architectures
+4 stars
from 1,901 · score 1.61
39.Project-AgML / AgML
AgML is a centralized framework for agricultural machine learning. AgML provides access to public agricultural datasets for common agricultural deep learning tasks, with standard benchmarks and pretrained models, as well the ability to generate synthetic data and annotations.
+4 stars
from 346 · score 1.61
40.azavea / raster-vision
An open source library and framework for deep learning on satellite and aerial imagery.
+3 stars
from 2,239 · score 1.39
41.junyanz / iGAN
Interactive Image Generation via Generative Adversarial Networks
+2 stars
from 4,011 · score 1.10
42.catalyst-team / catalyst
Accelerated deep learning R&D
+2 stars
from 3,386 · score 1.10
43.alankbi / detecto
Build fully-functioning computer vision models with PyTorch
+1 stars
from 622 · score 0.69
44.xiaoyufenfei / LEDNet
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
+1 stars
from 523 · score 0.69
45.vita-epfl / monoloco
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.
+1 stars
from 461 · score 0.69
46.wenbowen123 / iros20-6d-pose-tracking
[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
+1 stars
from 424 · score 0.69
47.stb-tester / stb-tester
Automated Testing for Set-Top Boxes and Smart TVs
+1 stars
from 194 · score 0.69
48.tensorlayer / DAGAN
The implementation code for "DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction"
+1 stars
from 180 · score 0.69