Update app.py

app.py

@@ -3,32 +3,40 @@ import tensorflow as tf
 from PIL import Image
 import numpy as np
 
-# Load your custom regression model
-model_path = "kia_mnist_keras_model.keras"
-
-#model.load_weights(model_path)
+# Laden des vortrainierten Pokémon-Modells
+model_path = "kia_pokemon_keras_model.h5"
 model = tf.keras.models.load_model(model_path)
 
-labels = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
+# Labels für den Pokémon Classifier 
+labels = [
+    'Balastoise','Charizard','Venusaur'
+]
 
-# Define regression function
-def predict_regression(image):
+def predict_pokemon(image):
     # Preprocess image
     image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
-    image = image.resize((28, 28)).convert('L') #resize the image to 28x28 and converts it to gray scale
+    image = image.resize((299, 299)) 
     image = np.array(image)
-    print(image.shape)
+    image = np.expand_dims(image, axis=0)  # same as image[None, ...]
+    
     # Predict
-    prediction = model.predict(image[None, ...])  # Assuming single regression value
-    confidences = {labels[i]: np.round(float(prediction[0][i]), 2) for i in range(len(labels))}
-    return confidences
+    predictions = model.predict(image)
+    prediction = np.argmax(predictions, axis=1)[0]
+    confidence = np.max(predictions)
+    
+    # Vorbereiten der Ausgabe
+    result = f"Predicted Pokémon: {labels[prediction]} with confidence: {confidence:.2f}"
+    return result
+
+# Erstellen der Gradio-Oberfläche
+input_image = gr.Image() 
+output_label = gr.Label()
+interface = gr.Interface(fn=predict_pokemon,
+                         inputs=input_image,
+                         outputs=output_label,
+                         examples=["Blastoise.jpg", "Charizard.png", "Venusaur.png"], 
+                         title="Pokémon Classifier",
+                         description="Drag and drop an image or select an example below to predict the Pokémon.")
 
-# Create Gradio interface
-input_image = gr.Image()
-output_text = gr.Textbox(label="Predicted Value")
-interface = gr.Interface(fn=predict_regression, 
-                         inputs=input_image, 
-                         outputs=gr.Label(),
-                         examples=["images/0.jpeg", "images/1.jpeg", "images/2.jpeg", "images/5.jpeg"],   
-                         description="A simple mlp classification model for image classification using the mnist dataset.")
+# Interface starten
 interface.launch()