---
license: agpl-3.0
datasets:
- KaraAgroAI/CADI-AI
language:
- en
library_name: yolo
tags:
- object detection
- vision
- yolo
pipeline_tag: object-detection
metrics:
- mape
---


## Cashew Disease Identification with AI (CADI-AI) Model

### Model Description

Object detection model trained using [YOLO v5x](https://github.com/ultralytics/yolov5/releases), a SOTA object detection algorithm.  
The model was pre-trained on the Cashew Disease Identification with AI (CADI-AI) train set (3788 images) at a resolution of 640x640 pixels. 
The CADI-AI dataset is available via [Kaggle](https://www.kaggle.com/datasets/karaagroaiprojects/cadi-ai) and 
[HuggingFace](https://huggingface.co/datasets/KaraAgroAI/CADI-AI).


## Intended uses

You can use the raw model for object detection on cashew images.

The model was initially developed to inform users whether cashew trees suffer from:
- pest infection, i.e. damage to crops by insects or pests
- disease, i.e. attacks on crops by microorganisms
- abiotic stress caused by non-living factors (e.g. environmental factors like weather or soil conditions or the lack of mineral nutrients to the crop).

KaraAgro AI developed the model for the initiatives 
[Market-Oriented Value Chains for Jobs & Growth in the ECOWAS Region (MOVE)](https://www.giz.de/en/worldwide/108524.html) and 
[FAIR Forward - Artificial Intelligence for All](https://www.bmz-digital.global/en/overview-of-initiatives/fair-forward/). 
Both initiatives are implemented by the Deutsche Gesellschaft für Internationale Zusammenarbeit (GIZ) on behalf of the German Federal Ministry for Economic Cooperation and Development (BMZ).

### How to use

- Load model and perform prediction:

```bash
pip install -U ultralytics
```

```python
from ultralytics import YOLO

# load model
model = YOLO("CADI-AI/yolov12x.pt")

# set confidence threshold
model.conf = 0.25

# perform inference
results = model("/path/to/your/image.jpg", size=640)

# parse results
for result in results:
    boxes = result.boxes.xyxy       # x1, y1, x2, y2
    scores = result.boxes.conf      # confidence scores
    categories = result.boxes.cls   # class indices
    print(result.names)             # {0: 'abiotic', 1: 'disease', 2: 'insect'}

# save results into "results/" folder
results[0].save(save_dir="results/")
```


- Finetune the model on your custom dataset:

```bash
yolo train data=data.yaml imgsz=640 batch=16 model=KaraAgroAI/CADI-AI epochs=10
```

### Model performance 

| Class | Precision | Recall | mAP@50 | mAP@50-95 |
| --- | --- | --- | --- | --- |
| all | 0.663 | 0.632 | 0.648 | 0.291 |
| insect | 0.794 | 0.811 | 0.815 | 0.39 |
| abiotic | 0.682 | 0.514 | 0.542 | 0.237 |
| disease | 0.594 | 0.571 | 0.588 | 0.248 |


### Demo 
[CADI-AI Spaces demonstration](https://huggingface.co/spaces/KaraAgroAI/CADI-AI)

### Project Repo 
If you want to know how the model and dataset has been used further for the GIZ-funded activity, please have a look at:
- The [GitHub repository](https://github.com/karaagro/cadi-ai) for the CADI AI desktop application

### Example prediction

<div align="center">
  <img width="640" alt="KaraAgroAI/CADI-AI" src="https://huggingface.co/KaraAgroAI/CADI-AI/resolve/main/sample.jpg">
</div>