Model Card for price-tag-classification

This image classification model was fine-tuned using the Ultralytics YOLO library.

Model Details

Model Description

• Developed by: Open Food Facts
• Model type: image classification
• License: agpl-3.0
• Finetuned from model: yolov8n-cls.pt

Training Details

Training Data

The model was fine-tuned using the following dataset: openfoodfacts/price-tag-classification (revision: v1.0).

Training Procedure

Dependency versions:

• ultralytics: 8.4.14
• pytorch: 2.9.0+cu128

Training Hyperparameters

• Epochs: 100
• Batch size: 4
• Image size: 960

Evaluation

The following evaluation metrics were obtained after training the model:

• metrics/accuracy_top1: 0.9489558935165405

• metrics/accuracy_top5: 1.0

• fitness: 0.9744779467582703

Evaluation on exported models

The model was also evaluated after exporting to ONNX and TensorRT formats. The following metrics were obtained:

ONNX export

• metrics/accuracy_top1: 0.9489558935165405

• metrics/accuracy_top5: 1.0

• fitness: 0.9744779467582703

Files

Most files stored on the repo are standard files created during training with the Ultralytics YOLO library.

What was added:

• an ONNX export of the trained model (best model), stored in weights/model.onnx.
• a Parquet file containing predictions on the full dataset, stored in predictions.parquet.
• metrics JSON files for each exported model format, stored in metrics_*.json:
  • metrics.json: metrics for the original PyTorch model
  • metrics_onnx.json: metrics for the ONNX exported model