🍅 Tomato Leaf Disease Detection Model (v1)

This model is designed to detect and classify tomato leaf diseases using deep learning (TensorFlow/Keras). It is trained on a curated dataset of tomato leaves, including healthy samples and various common diseases.

🧠 Model Details

Framework: TensorFlow / Keras
Format: .h5 (HDF5)
Model Type: CNN-based image classifier
Input: RGB image (resized to 256x256 or the model's expected input shape)
Output: Predicted class label (e.g., Healthy, Early Blight, Late Blight, etc.)

🏷️ Classes / Labels

Labels used during training are mapped using the class_indices.json file.

Example:

{
  "0": "Tomato_Bacterial_spot",
  "1": "Tomato_Early_blight",
  "2": "Tomato_Late_blight",
  "3": "Tomato_Leaf_Mold",
  "4": "Tomato_Septoria_leaf_spot",
  "5": "Tomato_Spider_mites_Two_spotted_spider_mite",
  "6": "Tomato__Target_Spot",
  "7": "Tomato__Tomato_YellowLeaf__Curl_Virus",
  "8": "Tomato__Tomato_mosaic_virus",
  "9": "Tomato_healthy"
}

📁 Files in This Repository

File	Description
`best_model.h5`	Final trained model
`tomato_disease_model_v1.h5`	Backup or alternate trained model
`class_indices.json`	Mapping of class names to label indices

🚀 How to Use

Load the Model and Predict

from tensorflow.keras.models import load_model
import json
import numpy as np
from tensorflow.keras.preprocessing import image

# Load model
model = load_model("best_model.h5")

# Load class indices
with open("class_indices.json", "r") as f:
    class_indices = json.load(f)

# Reverse class mapping
class_labels = {v: k for k, v in class_indices.items()}

# Load and preprocess image
img = image.load_img("path_to_image.jpg", target_size=(224, 224))
img_array = image.img_to_array(img)
img_array = np.expand_dims(img_array, axis=0) / 255.0

# Make prediction
prediction = model.predict(img_array)
predicted_class = class_labels[np.argmax(prediction)]

print(f"Predicted Disease: {predicted_class}")

📦 Intended Use

This model is intended for:

Research and prototyping
Agricultural assistance applications
Academic projects related to plant disease detection

Note: This model is not intended for medical or commercial agricultural decision-making without expert supervision.

📊 Training Details

Dataset: Custom dataset including images of tomato leaves with various diseases
Model: Custom CNN
Optimizer: Adam
Loss Function: Categorical Crossentropy
Accuracy Achieved: Approximately 94%

📜 License

This model is licensed under the Apache 2.0 License.

🙋‍♂️ Author

Abdullah Zunorain Email: [[email protected]] GitHub: https://github.com/abdullahzunorain

📌 Citation

@misc{abdullahzunorain2025tomato,
  title={Tomato Leaf Disease Detection Model (v1)},
  author={Abdullah Zunorain},
  year={2025},
  url={https://huggingface.co/abdullahzunorain/tomato_leaf_disease_det_model_v1},
  note={Hugging Face}
}

🔗 DOI

DOI: 10.57967/hf/5733

abdullahzunorain
/

tomato_leaf_disease_det_model_v1

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