| --- |
| license: agpl-3.0 |
| datasets: |
| - KaraAgroAI/CADI-AI |
| language: |
| - en |
| metrics: |
| - mape |
| library_name: yolo |
| tags: |
| - object detection |
| - vision |
| pipeline_tag: object-detection |
| --- |
| |
|
|
| ## 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. |
| 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: |
|
|
| ```python |
| import torch |
| import ultralytics |
| |
| # load model |
| model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5_0.65map_exp7_best.pt", |
| force_reload=False) |
| |
| # Images |
| img = ['/path/to/your_image.jpg']# batch of images |
| |
| # set model parameters |
| # set Non-Maximum-Suppression(NMS) threshold to define |
| # minimum confidence score that a bounding box must have in order to be kept. |
| 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: |
|
|
| ```bash |
| yolov5 train --data data.yaml --img 640 --batch 16 --weights 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 | |
|
|
| ### Limitations of the Model |
| The model has a few limitations that affect its performance in distinguishing between the disease class and the abiotic class. |
| The primary challenge lies in the similarity between these two classes within a typical farm setting. |
| The model may encounter difficulties in accurately differentiating between them due to their overlapping characteristics. |
| This limitation is an inherent challenge in the dataset and can impact the model's accuracy when classifying these classes. |
|
|
| However, it is worth noting that the model exhibits strong performance when it comes to the insect class. |
| This is attributed to the distinct characteristics of insect class, which make them easier to identify and classify accurately. |
|
|
| ### Example prediction |
|
|
| <div align="center"> |
| <img width="640" alt="KaraAgroAI/CADI-AI" src="https://huggingface.co/KaraAgroAI/CADI-AI/resolve/main/sample.jpg"> |
| </div> |
