You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Pycnidia Detection Model

The YOLOv8 object detection model has been fine-tuned to detect pycnidia, the asexual reproductive structures of the fungal pathogen Zymoseptoria tritici on leaves of winter wheat, on 512×512 pixel image patches. These patches are from leaf images scanned using a flatbed scanner at 1200 dpi. The resulting model weights are saved as pycnidia-detection-model-512x512.onnx.

This model is designed to be used in conjunction with a tiling approach, in which full leaf images are split into 512×512 patches prior to inference.

Recall: 79% Precision: 81%

Example of Pycnidia Detection:

If you use this model in your work, please cite:

Rich, J. (2025). pycnidia-detection (Revision 831db6d). Hugging Face. https://doi.org/10.57967/hf/5705

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for jbr819/pycnidia-detection

Base model

Ultralytics/YOLOv8

Finetuned

(98)

this model