metadata
license: cc-by-sa-4.0
datasets:
- KaraAgroAI/CADI-AI
language:
- en
metrics:
- mape
pipeline_tag: object-detection
tags:
- object detection
- vision
Cashew Disease Identification with AI (CADI-AI) Model
Model Description
Object detection model trained using YOLO v5x. The model was pre-trained on the Cashew Disease Identification with AI (CADI-AI) train set (3788 images) at a resolution of 640x640 pixels. CADI-AI dataset is available in hugging face dataset hub
Intended uses & limitations
You can use the raw model for object detection on cashew images.
How to use
- Load model and perform prediction:
import torch
# load model
model = torch.hub.load('ultralytics/yolov5', 'KaraAgroAI/CADI-AI')
# Images
img = ['/path/to/CADI-AI-image.jpg']# batch of images
# set model parameters
model.conf = 0.20 # NMS confidence threshold
# perform inference
results = model(img, size=640)
# Results
results.print()
results.xyxy[0] # img1 predictions (tensor)
results.pandas().xyxy[0] # img1 predictions (pandas)
# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]
# show detection bounding boxes on image
results.show()
# save results into "results/" folder
results.save(save_dir='results/')
- Finetune the model on your custom dataset:
yolov5 train --data data.yaml --img 640 --batch 16 --weights KaraAgroAI/CADI-AI --epochs 10
Performances/Benchmarks of the model
| Precision | Recall | mAP50 | mAP50-95 |
|---|---|---|---|
| 0.663 | 0.632 | 0.648 | 0.291 |
Example prediction
