app.py

# import gradio as gr
# import torch
# from torchvision import transforms
# from PIL import Image

# # Load your pre-trained model
# # Example: Replace 'YourModelClass' with your actual model class
# from your_module import YourModelClass

# model = YourModelClass()
# model.load_state_dict(torch.load('path/to/your/model_weights.pth'))
# model.eval()

# # Define transformations for input images
# transform = transforms.Compose([
#     transforms.Resize((224, 224)),
#     transforms.ToTensor(),
#     transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
# ])

# # Define the function for making predictions
# def predict_leaf_health(image):
#     try:
#         # Open and preprocess the image
#         img = Image.open(image)
#         img = transform(img)
#         img = img.unsqueeze(0)  # Add batch dimension

#         # Make prediction
#         with torch.no_grad():
#             output = model(img)
#             prediction = torch.argmax(output).item()

#         # Map the prediction to class labels (modify as needed)
#         class_labels = {0: 'Unhealthy', 1: 'Healthy'}
#         result = class_labels.get(prediction, 'Unknown')

#         return result

#     except Exception as e:
#         return f"Error: {str(e)}"

# # Create Gradio Interface
# iface = gr.Interface(
#     fn=predict_leaf_health,
#     inputs=gr.Image(type="file", label="Upload an image of a plant leaf"),
#     outputs="text",
#     theme="default",
#     title="Plant Leaf Health Classification",
#     description="Upload an image of a plant leaf to classify its health.",
# )

# # Launch the Gradio Interface
# iface.launch()
import torch
from torchvision import transforms
from PIL import Image

# Define your model class
class YourModelClass(torch.nn.Module):
    # Define your model architecture here

# Create an instance of your model
    model = YourModelClass()

# Load the pre-trained weights
model.load_state_dict(torch.load('model_weights.pth'))
model.eval()
def predict_leaf_health(image_path):
    try:
        # Open and preprocess the image
        img = Image.open(image_path)
        transform = transforms.Compose([
            transforms.Resize((224, 224)),
            transforms.ToTensor(),
            transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
        ])
        img = transform(img)
        img = img.unsqueeze(0)  # Add batch dimension

        # Make prediction
        with torch.no_grad():
            output = model(img)
            prediction = torch.argmax(output).item()

        # Map the prediction to class labels (modify as needed)
        class_labels = {0: 'Unhealthy', 1: 'Healthy'}
        result = class_labels.get(prediction, 'Unknown')

        return result

    except Exception as e:
        return f"Error: {str(e)}"