Image-level Classification Example

Introduction

Image classification assigns labels to an entire image. X-AnyLabeling supports multiclass and multilabel classification.

Multiclass classification assigns exactly one class to each image.

Multilabel classification allows each image to have multiple labels.

Step 0: Preparation

Prepare a flags file like logo_flags.txt or fruit_flags.txt. An example is shown below:

Apple
Meta
Google

Step 1: Run the Application

python anylabeling/app.py

Step 2: Upload the Configuration File

Click on Upload -> Upload Image Flags File in the top menu bar and select the prepared configuration file to upload.

Option 1: Quick Start

Tip

This option is suitable for a quick startup.

python anylabeling/app.py --flags Apple,Meta,Google

Caution

Separate labels with commas.

Option 2: Using a Configuration File

python anylabeling/app.py --flags flags.txt

Note

Each line in the file represents one category.

For detailed output examples, refer to this folder.