Plant Disease Detection

[keshripritesh]

🌱 Plant Disease Detection

A deep learning-based project aimed at detecting plant diseases from images using PyTorch models. This project is part of GirlScript Summer of Code (GSSoC’25) contributions.

---

🎯 Aim

The goal of this project is to help farmers and agricultural researchers by providing an AI-powered solution for detecting plant diseases early, thereby improving crop health and productivity.

---

📂 Project Contents

• plant-disease-model.pth & plant-disease-model-complete.pth → Pre-trained PyTorch models for disease classification
• test/ → Sample test images (healthy & diseased plants)
• Screenshot 2025-06-19 175549.png, Screenshot 2025-06-19 175613.png, Screenshot 2025-06-19 175628.png → Example model prediction screenshots

---

🛠️ Steps Involved

• Collecting and preprocessing plant disease dataset
• Training deep learning models (PyTorch CNNs)
• Saving trained models for inference
• Testing using sample images
• Visualizing model outputs with prediction screenshots

---

🤖 Model Used

• Pre-trained PyTorch CNN models (saved as .pth files)

---

📚 Libraries Required

• torch
• torchvision
• numpy
• pandas
• matplotlib
• PIL

---

🚀 Usage

Example inference code:

import torch
from PIL import Image
from torchvision import transforms

# Load model
model = torch.load('plant-disease-model.pth')
model.eval()

# Preprocess input
transform = transforms.Compose([
    transforms.Resize((224,224)),
    transforms.ToTensor(),
])
img = Image.open("test/sample_leaf.jpg")
input_tensor = transform(img).unsqueeze(0)

# Prediction
with torch.no_grad():
    output = model(input_tensor)
    predicted_class = output.argmax(dim=1).item()
print("Predicted Class:", predicted_class)

---

📸 Output Snapshots

• Example predictions shown in:

---

✅ Conclusion

The project demonstrates how deep learning can be applied to agriculture by providing an automated method to classify plant diseases.

---

[github-actions]

Thank you for raising this issue!

We'll review it as soon as possible. We truly appreciate your contributions! ✨

Meanwhile make sure you've visited the README.md, CONTRIBUTING.md, and CODE_OF_CONDUCT.md before creating a PR for this. Also, please do NOT create a PR until this issue has been assigned to you. 😊