Update app.py

app.py

@@ -1,39 +1,40 @@
 import gradio as gr
-import numpy as np
+import tensorflow as tf
 from PIL import Image
-from tensorflow.keras.models import load_model
-from tensorflow.keras.preprocessing.image import img_to_array
+import numpy as np
+
+# Load the pre-trained Pokémon model
+model_path = "pokemon_classifier_model.keras"
+model = tf.keras.models.load_model(model_path)
 
-# Assuming your model and class names are loaded correctly
-model = load_model('pokemon_classifier_model.keras')
-classes = ['Doduo', 'Geodude', 'Zubat']
+# Define the Pokémon classes
+classes = ['Doduo', 'Geodude', 'Zubat']  # Adjust classes based on what your model was trained on
 
+# Define the image classification function
 def classify_image(image):
     try:
-        # Image preprocessing
-        image = image.resize((150, 150))
-        image_array = img_to_array(image)
-        image_array = image_array.reshape((1, 150, 150, 3))
-        image_array /= 255.0
-        
-        # Model prediction
+        # Preprocess the image to match the model's input expectations
+        image = Image.fromarray(image.astype('uint8'), 'RGB')  # Ensure image is in RGB
+        image = image.resize((150, 150))  # Resize to the input size your model expects
+        image_array = np.array(image) / 255.0  # Convert to array and normalize
+        image_array = np.expand_dims(image_array, axis=0)  # Add batch dimension
+
+        # Predict using the model
         prediction = model.predict(image_array)
         predicted_class = classes[np.argmax(prediction)]
         confidence = np.max(prediction)
-        
-        return predicted_class, f"{confidence * 100:.2f}% Confidence"
+
+        return f"Predicted Class: {predicted_class}, Confidence: {np.round(confidence * 100, 2)}%"
     except Exception as e:
-        # Catch and print any error that occurs
-        print(f"Error during model prediction: {e}")
-        return "Error in prediction", "Error"
+        return str(e)  # Return the error message if failure
 
-# Gradio app setup
-iface = gr.Interface(
-    fn=classify_image,
-    inputs=gr.Image(),
-    outputs=[gr.Text(), gr.Text()],
-    title="Pokémon Image Classifier",
-    description="Upload an image of a Pokémon to classify!"
-)
+# Create Gradio interface
+input_image = gr.inputs.Image(shape=(150, 150))
+output_label = gr.outputs.Label(num_top_classes=3)
+interface = gr.Interface(fn=classify_image,
+                         inputs=input_image,
+                         outputs=output_label,
+                         examples=["path/to/example1.jpg", "path/to/example2.jpg"],  # Update with real paths if needed
+                         description="Upload an image of a Pokémon to classify!")
 
-iface.launch()
+interface.launch()