# datitran/raccoon_dataset

The dataset is used to train my own raccoon detector and I blogged about it on Medium

Repository: https://github.com/datitran/raccoon_dataset
Canonical: https://ross.abutalabs.com/products/raccoon_dataset
Homepage: https://medium.com/towards-data-science/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: tensorflow-experiments, dataset
Last push: 2021-10-12T12:49:25+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3324, "days_push": 1786, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1268, forks 949 (observed 2026-08-28T04:04:11.508687+00:00)

## What it is
A small open dataset of 200 labeled raccoon images (160 train / 40 validation) with PASCAL VOC XML annotations, created to train an object detector with TensorFlow's Object Detection API. It also includes helper scripts and notebooks for converting annotations to CSV and generating TFRecord files.

## Use cases
- train an object detection model on raccoon images
- get a small labeled dataset for testing TensorFlow Object Detection API
- convert PASCAL VOC XML annotations to CSV
- generate TFRecord files for object detection training
- learn how to build a custom object detector from scratch
- practice drawing bounding boxes on annotated images

## When to choose
- you need a tiny, simple dataset to prototype object detection pipelines
- you're following a tutorial on TensorFlow Object Detection API
- you want example PASCAL VOC annotations and conversion scripts

## When to avoid
- you need a large or diverse dataset for production-grade detection
- you need classes beyond raccoons
- you work with frameworks other than TensorFlow and don't want to convert formats

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, image-processing, computer-vision
- domain: machine-learning, computer-vision, image-processing
- platform: python
- tags: object-detection, tensorflow, pascal-voc, raccoon-detector, image-annotation, tutorial

## Member repositories
- datitran/raccoon_dataset (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:11.508687+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 2026-08-30T05:03:37.258581+00:00, confidence not recorded.
  - readme: https://github.com/datitran/raccoon_dataset (fetched 2026-08-28T04:04:11.508687+00:00, sha ef96d621f4d8)
- Data as of 2026-08-30T08:39:29.467469+00:00.