Delete app.py

app.py

@@ -1,64 +0,0 @@
-import gradio as gr
-import torch
-from torchvision import transforms as tt
-from PIL import Image
-
-# Load models
-potato_model = torch.load("models/potato_model_statedict__f.pth", map_location=torch.device('cpu'))
-tomato_model = torch.load("models/tomato_model_statedict__f.pth", map_location=torch.device('cpu'))
-
-# Set both models to evaluation mode
-potato_model.eval()
-tomato_model.eval()
-
-# Prediction function for Potato and Tomato models
-def predict(image, model_type):
-    # Define transformations
-    transforms = tt.Compose([
-        tt.Resize((224, 224)),
-        tt.ToTensor()
-    ])
-    
-    # Open image and apply transforms
-    image = Image.open(image).convert("RGB")
-    image_tensor = transforms(image).unsqueeze(0)
-
-    # Choose the correct model
-    model = potato_model if model_type == 'Potato' else tomato_model
-
-    # Perform prediction
-    with torch.no_grad():
-        output = model(image_tensor)
-    
-    probabilities = torch.nn.functional.softmax(output[0], dim=0)
-    predicted_class = torch.argmax(probabilities).item()
-    predicted_probability = probabilities[predicted_class].item()
-
-    # Define class labels
-    if model_type == 'Potato':
-        class_labels = ['Potato Early Blight', 'Potato Late Blight', 'Potato Healthy']
-    else:
-        class_labels = ['Tomato Early Blight', 'Tomato Late Blight', 'Tomato Healthy']
-
-    return {
-        "Class": class_labels[predicted_class],
-        "Probability (%)": round(predicted_probability * 100, 2)
-    }
-
-# Gradio Interface
-def inference(image, model_type):
-    prediction = predict(image, model_type)
-    return prediction
-
-gr.Interface(
-    fn=inference,
-    inputs=[
-        gr.Image(type="file", label="Upload an Image"),
-        gr.Radio(["Potato", "Tomato"], label="Model Type", value="Potato")
-    ],
-    outputs=[
-        gr.Label(label="Prediction"),
-    ],
-    title="Plant Disease Classification",
-    description="Upload an image to predict whether the plant is healthy or has a disease."
-).launch()