# open-edge-platform/geti

Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, with CPU, Intel XPU, and NVIDIA CUDA support.

Repository: https://github.com/open-edge-platform/geti
Canonical: https://ross.abutalabs.com/products/geti
Homepage: https://docs.geti.intel.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: openvino, computer-vision, deep-learning, pytorch, neural-networks-compression, quantization, image-classification, image-segmentation, object-detection, self-supervised-learning, semi-supervised-learning, transfer-learning, automl, machine-learning, incremental-learning, geti
Last push: 2026-08-26T14:18:17+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 97, longevity 100
- inputs: {"age_days": 2868, "days_push": 7, "days_rel": 20, "gap_med": 28.5, "n_releases_24m": 15}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1317, forks 477 (observed 2026-08-28T04:04:20.971779+00:00)

## What it is
Geti is an open-source, end-to-end Vision AI application from Intel that takes users from raw images to deployed computer vision models, running locally as a single container or native Windows app. It includes the getitune training engine (formerly OpenVINO Training Extensions/otx) with 67+ state-of-the-art model architectures for object detection, segmentation, and classification, optimized for inference on Intel XPU, CPU, and NVIDIA CUDA hardware.

## Use cases
- train object detection models on my own images
- build an image classification model with minimal data
- train image segmentation models locally
- optimize and quantize vision models for edge inference with OpenVINO
- run AutoML to find the best computer vision model for my dataset
- deploy a vision model for live inference on Intel GPU
- do transfer learning from pretrained YOLO or DETR models
- annotate images and manage datasets for vision training

## When to choose
- you want an end-to-end local workflow from raw images to deployed vision models
- you target Intel hardware (CPU, XPU) or NVIDIA CUDA for training and inference
- you need state-of-the-art detection, segmentation, or classification architectures without writing training code
- you want OpenVINO-optimized models for edge deployment
- you prefer a self-hosted GUI application or REST API over notebooks

## When to avoid
- you need tasks beyond computer vision such as NLP, audio, or LLMs
- you require cloud-scale distributed training across many nodes
- you want a lightweight Python library only - though getitune covers that, the full app is heavyweight
- you depend on non-Intel accelerators other than NVIDIA CUDA
- you need the deprecated otx package API specifically

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, deep-learning, computer-vision, image-processing, llm-training
- domain: computer-vision, machine-learning, deep-learning, image-processing
- platform: windows, python, self-hosted
- tags: openvino, automl, object-detection, image-segmentation, image-classification, model-optimization, quantization, transfer-learning, edge-ai, intel-xpu, nvidia-cuda, vision-ai, docker, linux, gpu

## Member repositories
- open-edge-platform/geti (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.971779+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:48:13.678101+00:00, confidence not recorded.
  - readme: https://github.com/open-edge-platform/geti (fetched 2026-08-28T04:04:20.971779+00:00, sha 8f933e9871f7)
  - homepage: https://docs.geti.intel.com (fetched 2026-08-29T12:07:01.408660+00:00, sha 53a184193773)
  - site_page: https://docs.geti.intel.com/docs/rest-api/openapi-specification (fetched 2026-08-29T12:07:01.422543+00:00, sha f9b535bc6b6f)
  - site_page: https://docs.geti.intel.com/docs/2.0/user-guide/getting-started/introduction (fetched 2026-08-29T12:07:01.424016+00:00, sha f9b535bc6b6f)
  - site_page: https://docs.geti.intel.com/docs/user-guide/learn-geti/computer-vision-tasks/ai-fundamentals-tasks (fetched 2026-08-29T12:07:01.425953+00:00, sha f9b535bc6b6f)
  - site_page: https://docs.geti.intel.com/docs/user-guide/geti-fundamentals/datasets/dataset-management (fetched 2026-08-29T12:07:01.427394+00:00, sha f9b535bc6b6f)
  - site_page: https://docs.geti.intel.com/docs/user-guide/geti-fundamentals/model-training-and-optimization (fetched 2026-08-29T12:07:01.428877+00:00, sha f9b535bc6b6f)
  - site_page: https://docs.geti.intel.com/docs/user-guide/getting-started/introduction (fetched 2026-08-29T12:07:01.417693+00:00, sha f9b535bc6b6f)
  - site_page: https://docs.geti.intel.com/docs/rest-api/get-started (fetched 2026-08-29T12:07:01.419394+00:00, sha f9b535bc6b6f)
  - site_page: https://docs.geti.intel.com/docs/2.0/rest-api/openapi-specification (fetched 2026-08-29T12:07:01.421020+00:00, sha f9b535bc6b6f)
- Data as of 2026-08-30T08:39:29.467469+00:00.