Object Detection with YOLO

Provides an example project for running YOLO (You Only Look Once) on Valohai. It includes scripts and configurations for training and deploying YOLO models for real-time object detection tasks.

---

Overview

This project demonstrates:

• Training YOLOv5 and YOLOv5-Seg models

• Validating trained models

• Running YOLOv8 for inference and ONNX export

• Using datasets stored in S3 with Valohai inputs and outputs

---

Steps

1

Data Preparation

Store datasets in Amazon S3 and configure Valohai inputs for retrieval and processing in training.

2

Configuration in Valohai

Set up Valohai pipelines to automate the training, validation, and inference stages.

3

Training Execution

Execute training runs on YOLOv5 and YOLOv5-Seg with predefined configurations to start building robust models for object detection.

4

Validation Process

Conduct validation on trained models to compare predicted results against benchmark datasets, refining model performance accordingly.

5

Inference Implementation

Deploy YOLOv8 for inference tasks, focusing on optimizing speed and accuracy. Transition the model to ONNX format when necessary for enhanced compatibility.

---

GitHub repository

The repository walks you through how to go through the above steps:

GitHub - valohai/yolo-example: Valohai YOLO ExamplesGitHub