# experiencor/keras-yolo2

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).

Repository: https://github.com/experiencor/keras-yolo2
Canonical: https://ross.abutalabs.com/products/keras-yolo2
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: convolutional-networks, deep-learning, yolo2, realtime, regression
Last push: 2023-03-24T22:26:55+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3451, "days_push": 1258, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1733, forks 771 (observed 2026-08-28T04:05:28.913123+00:00)

## What it is
A Keras/TensorFlow implementation of the YOLOv2 real-time object detection model with support for training on custom datasets. It offers multiple backend architectures including Full YOLO, Tiny YOLO, MobileNet, SqueezeNet, InceptionV3, and ResNet50.

## Use cases
- train a yolo object detector on my own images
- detect raccoons or animals in photos
- real-time object detection with keras
- train yolov2 with a mobilenet backend
- object detection from VOC-format annotations
- build a custom detector for hands or cells

## When to avoid
- you need the latest YOLO versions (YOLOv4/v5/v8) or state-of-the-art accuracy
- you require multi-GPU or multiscale training, which are unimplemented
- you need active maintenance or modern TensorFlow 2.x compatibility
- you want a production-ready detector with mAP evaluation built in

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: deep-learning, computer-vision, machine-learning, image-processing
- platform: python, cross-platform
- tags: yolo, object-detection, keras, tensorflow, realtime-detection, custom-training, mobilenet, voc-annotations

## Member repositories
- experiencor/keras-yolo2 (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:28.913123+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 2026-08-30T03:31:27.294264+00:00, confidence not recorded.
  - readme: https://github.com/experiencor/keras-yolo2 (fetched 2026-08-28T04:05:28.913123+00:00, sha 66262605778c)
- Data as of 2026-08-30T08:39:29.467469+00:00.