📜
Developer Documentation
  • 👋EyePop.ai Introduction
  • 🎯Getting Started
    • 👨‍💻Pop Quick Start
    • 💪Low Code Examples
  • 🗝️API Key
  • 🏷️Finding People & Objects
  • SDKs
    • ☁️React/Node SDK
      • Render 2D (Visualization)
      • Composable Pops
    • 🐍Python SDK
      • Composable Pops
  • Page 2
  • Self Service Training
    • Dataset SDK (Node)
    • 🏋️How To Train a Model
      • Defining Your Computer Vision Model
      • Example Use Case: Detecting Eyeglasses
      • Preparing & Uploading Data
      • Using EyePop.ai’s AutoLabeler
      • Human Review
      • Data Augmentation Setup
      • Training in Progress
      • Deployment
      • Previewing Results
      • Iterative Training
      • Deep Dives (FAQ)
  • FAQ
  • EyePop.ai Visual Intelligence
    • Visual Intelligence
    • Reports
  • Deployment
    • On Premise IP Camera analysis
    • Windows Application Runtime
Powered by GitBook
On this page
  • Overview
  • What Are Negative Images?
  • How to Organize Your Dataset
  • How to Upload Negative Images
  • Best Practices for Negative Images
  • Recommended Dataset Ratios
  • Frequently Asked Questions
  1. Self Service Training
  2. How To Train a Model

Preparing & Uploading Data

Overview

A good place to start when creating and training a new model is with a dataset containing at least 500 images. Include diverse lighting, angles, and contexts for real-world applicability. The dataset should also include negative images. Negative images do not include the target object, and are helpful to reduce false positives in your trained model. With a beginning dataset of 500 images, aim for 400 images (or 80%) showing your object, and 100 (20%) negative images.

What Are Negative Images?

Negative images are photos that do NOT contain your target object. These images are crucial for training your model to distinguish between what you want to detect and what you don't.

Why Use Negative Images?

  • Reduce false positives: Help your model learn what NOT to classify as your target object

  • Improve accuracy: Train the model to be more discriminating

  • Handle similar objects: Teach the model to distinguish between similar-looking items

Examples of Negative Images:

  • If training a door detection model: Include images of windows, archways, or openings that are NOT doors

  • If training a car detection model: Include images of trucks, motorcycles, or street scenes without cars

  • If training a person detection model: Include images of mannequins, statues, or scenes without people

How to Organize Your Dataset

Folder Structure

Organize your images into clear folder structures before uploading:

your-dataset/
├── positive-images/
│   ├── door_001.jpg
│   ├── door_002.jpg
│   └── ... (400 images of doors)
└── negatives/
    ├── window_001.jpg
    ├── archway_001.jpg
    └── ... (100 images without doors)

Important: The folder containing negative images must be named "negatives" (all lowercase, plural).

How to Upload Negative Images

Step-by-Step Process:

  1. Prepare your negative images folder

    • Create a folder named exactly negatives (lowercase, plural)

    • Add approximately 100 images that do NOT contain your target object

    • Ensure images show similar contexts or potentially confusing objects

  2. Navigate to the upload interface

    • Go to the Models tab in the sidebar

    • Find your Image Collection

    • Click the three dots (...) menu next to your dataset

    • Select Upload

  3. Upload the negatives folder

    • On the upload screen, locate the "add more images" tile

    • Drag and drop or upload your entire negatives folder onto this tile

    • The system will automatically recognize this as negative training data

Upload Tips:

  • You can drag and drop the entire folder at once

  • The upload area will accept the folder and process all images inside

  • Make sure your folder is named exactly "negatives" for proper recognition

Best Practices for Negative Images

Quality Guidelines:

  • Similar contexts: Use images from similar environments where your target object might appear

  • Potential confusers: Include objects that might be mistaken for your target (like windows when training for doors)

  • Varied conditions: Include different lighting, angles, and backgrounds

  • High quality: Use clear, well-lit images similar to your positive examples

Common Mistakes to Avoid:

  • Don't use completely unrelated images (random landscapes for a door model)

  • Avoid low-quality or blurry negative images

  • Don't include images that partially show your target object

  • Don't forget to name the folder exactly "negatives"

Recommended Dataset Ratios

Dataset Size
Positive Images
Negative Images
Ratio

500 images

400 images

100 images

80/20

1000 images

800 images

200 images

80/20

2000+ images

1600+ images

400+ images

80/20

Frequently Asked Questions

Q: How do I upload negative images?

A: Create a folder named "negatives" with ~100 images that don't contain your target object. Go to Models → click the three dots (...) on your dataset → select Upload → drag and drop the "negatives" folder onto the "add more images" tile.

Q: What should negative images contain?

A: Images that are similar to where your target object appears, but without the target object itself. For example, if training a door model, include images of windows, archways, or wall sections that might be confused for doors.

Q: How many negative images do I need?

A: Start with about 20% of your total dataset as negative images. For a 500-image dataset, use approximately 100 negative images.

Q: Can I add negative images after initial training?

A: Yes, you can upload additional negative images to improve your model's performance and reduce false positives.


PreviousExample Use Case: Detecting EyeglassesNextUsing EyePop.ai’s AutoLabeler

Last updated 12 days ago

🏋️