Update app.py

app.py

@@ -1,3 +1,39 @@
 import gradio as gr
+import torch
+from torchvision import transforms as tt
+from PIL import Image
+from predict import predict_potato, predict_tomato  # Ensure these functions are defined to use your models
+from model import model_potato, model_tomato  # Ensure these models are correctly defined in your script
 
-gr.load("models/hassaanik/Plant_Disease_Classification").launch()
+# Load models (assuming they are saved in the "models" directory within the Hugging Face Space)
+model_potato.load_state_dict(torch.load("models/potato_model_statedict__f.pth", map_location=torch.device('cpu')))
+model_tomato.load_state_dict(torch.load("models/tomato_model_statedict__f.pth", map_location=torch.device('cpu')))
+
+# Define a function to make predictions based on the selected model
+def classify_image(image, plant_type):
+    if plant_type == "Potato":
+        class_name, probability = predict_potato(image, model_potato)
+    else:
+        class_name, probability = predict_tomato(image, model_tomato)
+
+    return {
+        "Predicted Class": class_name,
+        "Confidence (%)": f"{probability * 100:.2f}%"
+    }
+
+# Set up Gradio interface
+iface = gr.Interface(
+    fn=classify_image,
+    inputs=[
+        gr.inputs.Image(type="file", label="Upload an Image"),
+        gr.inputs.Radio(["Potato", "Tomato"], label="Select Plant Type")
+    ],
+    outputs=[
+        gr.outputs.Label(num_top_classes=1, label="Prediction Results")
+    ],
+    title="Potato and Tomato Disease Classification",
+    description="Upload an image of a potato or tomato leaf to classify the disease."
+)
+
+# Launch Gradio interface
+iface.launch()