OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Trainyourownyolo

Trainyourownyolo is a public repository of tutorial materials and code for building custom image object detectors with YOLOv3. Its workflow covers image annotation, model training and inference on new images or videos, with an included cat-face inference example.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Trainyourownyolo — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a repository-based path from image annotation through custom YOLOv3 training to inference, or when you want to try the included cat-face detection example.

Who it is for

  • Developers and learners building a YOLOv3 detector for a custom image dataset.
  • Users who want a guided annotation, training and inference workflow.

Documented uses

  • Annotate images for an object-detection dataset using VoTT.
  • Train a custom YOLOv3 detector from annotated images and pre-trained weights.
  • Run inference on new images or videos.
  • Try the included cat-face detector and save bounding-box results.
Before you choose

Requirements & limits

The repository is public and described as open source. Its README displays a CC BY 4.0 license badge.

  • The README specifies Python 3.6 or 3.7 and identifies TensorFlow 2.3 and Keras 2.4.
  • A CUDA-capable GPU is recommended for faster training; Google Colab can skip most setup.
  • The documented training workflow depends on annotated images and downloaded pre-trained weights.
  • Weights & Biases experiment tracking is optional and requires its own account and API key.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run the included cat-face inference example

Generate bounding-box results for the repository’s sample cat images.

Before you start

  • Python 3.6 or 3.7
  • A cloned repository and its required packages installed in a virtual environment

Steps

  1. Open a terminal in the repository’s root folder with the virtual environment active.

  2. Run the command below.

    Documented command
    python Minimal_Example.py

Expected outcome

The example writes annotated test images with bounding boxes and confidence scores, along with a Detection_Results.csv file.

Guide limitations

  • This is inference with the included cat-face detector, not training a custom model.
  • The README reports typical CPU inference speed of approximately two images per second.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
22 October 2026
Original website title
AntonMu/TrainYourOwnYOLO · Official homepage title · retained in its source language
How we review sourcesSuggest a correction