openfoodfacts/crop-detection
By openfoodfacts · ↓ 7 · ♥ 0 · Updated 2024-09-27
What's in this repo
This page lists the files in openfoodfacts/crop-detection, including best.onnx.
- 1 ONNX models (.onnx files)
- 44 files, including 16 .jpg, 13 .png, 2 .yaml, 2 .pt, 2 .tflite, 2 .pb
- Last updated 2024-09-27
ONNX files
| File | Size | Download |
|---|---|---|
| weights/best.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
base_model: Ultralytics/YOLOv8 license: agpl-3.0 datasets:
- openfoodfacts/crop-detection-dataset
Crop detection
When contributors use the mobile app, they are asked to take pictures of the product, then to crop it. To assist users during the process, we create a crop-detection model desin to detect the product edges.
The base model, Yolov8n, was fine-tuned on manually annotated images extracted from the Open Food Facts database using Label Studio. The explanation about the image extraction can be found in the Product Opener documentation.
Evaluation metric:
- mAP50_95: 0.895
Model info
Created: 2024-09-27
Updated: 2024-09-27
View on Hugging FaceFiles (44)
Related models
More from openfoodfacts
More models
No task type declared.