Update app.py

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import os
 import tensorflow as tf
 from PIL import Image
 import numpy as np
@@ -10,33 +11,27 @@ model = tf.keras.models.load_model('plant_disease_classifier.h5')
 # Defining function for predictions
 def predict(input_image):
     try:
-        input_image = img_to_array(input_image) # Converting picture to array
-
-        # Preprocessing 
-        input_image = np.resize(input_image, (256,256,3))
-        input_image = np.array(input_image).astype(np.float32) / 255.0
-        input_image = np.expand_dims(input_image, axis = 0)
-
-        prediction = model.predict(input_image)
+        input_image = tf.convert_to_tensor(input_image)
+        input_image = tf.image.resize(input_image, [256, 256])
+        input_image = tf.expand_dims(input_image, 0) / 255.0
 
+        predictions = model.predict(input_image)
         labels = ['Healthy', 'Powdery', 'Rust']
 
-        preds_class = np.argmax(preds)
-        preds_label = labels[preds_class]
+        class_idx = np.argmax(predictions)
+        class_label = labels[class_idx]
+        confidence = predictions[0][class_idx]
 
-        output = f"Predicted Class: {preds_label} <br><br> Confidence Score: {preds[0][preds_class]}"
+        return f"Predicted Class: {class_label} <br><br> Confidence Score: {confidence}"
 
-        return output
     except Exception as e:
-        return str(e)
+        return f"An error occurred: {e}"
 
-examples = ["Healthy.png",
-           "Powdery.png",
-           "Rust.png"]
+examples = ["Healthy.png", "Powdery.png", "Rust.png"]
 
 iface = gr.Interface(
     fn = predict,
-    inputs = gr.inputs.Image(shape=(256,256)),
+    inputs = gr.Interface.Image(shape=(256,256)),
     outputs = "text",
     title = "🌿 Plant Disease Detection",
     description='<br> This is a specialized Image Classification model engineered to identify the health status of plants, specifically detecting conditions of Powdery Mildew or Rust. <br> \