TRIA: TRIchogrammA parasitized egg count.
Description
TRIA is an ultralytics model that identificate eggs of Ephestia kuehnniella previously parasitized by Trichogramma wasps. TRIA was initialized on YOLO11 and trained on a specific datasets.
Installation
- You need https://docs.ultralytics.com/fr#where-to-start. You can install the Ultralytics package using pip. Here's a basic installation command (in a terminal):
pip install ultralytics
- You need to download the trained model "tria-v1.pt".
Usage
You can just call the model on the pictures you want to annotate (imagine that the pictures are in the folder "pictures2count") with the following command (in a terminal, in the same folder where "tria-v1.pt" was saved):
yolo predict model=tria-v1.pt source=pictures2count/ save_txt=True
The model will create a folder "runs/detect/predict" with the annotated image and a folder "labels/" with the annotation in ".txt" format.
Example
Low density
| Initial image | Prediction |
|---|---|
| (/example/example_init_low.png) | (/example/example_predict_low.png) |
High density
| Initial image | Prediction |
|---|---|
| (/example/example_init_high.png) | (/example/example_predict_high.png) |
Limits
This model only works with image sizes similar to the example.
Authors and acknowledgment
- C. BRESCH (INRAE) annotated the images.
- L. VAN OUDENHOVE (INRAE) led the project.
- Thanks to J. DE GOËR and L. PETITCOLIN for advices.
- The CoLab.Ia platform provided the GPU for training.
Contact
License
GNU GENERAL PUBLIC LICENSE, v3.