Update app.py

app.py

@@ -3,27 +3,33 @@ import tensorflow as tf
 from tensorflow.keras.preprocessing import image
 import numpy as np
 
-# Modell laden
-model = tf.keras.models.load_model('pokemon_classifier_model.keras')
+# Modell laden mit Fehlerbehandlung
+try:
+    model = tf.keras.models.load_model('pokemon_classifier_model.keras')
+except Exception as e:
+    print(f"Fehler beim Laden des Modells: {e}")
 
 # Klassenlabels
 class_names = ['Bisasam', 'Schiggy', 'Glumanda']
 
 # Vorhersagefunktion
 def predict(img):
-    img = img.resize((224, 224))
-    img_array = np.array(img)
-    img_array = np.expand_dims(img_array, axis=0)
-    img_array = tf.keras.applications.vgg16.preprocess_input(img_array)
+    try:
+        img = img.resize((224, 224))
+        img_array = np.array(img)
+        img_array = np.expand_dims(img_array, axis=0)
+        img_array = tf.keras.applications.vgg16.preprocess_input(img_array)
 
-    predictions = model.predict(img_array)
-    score = tf.nn.softmax(predictions[0])
+        predictions = model.predict(img_array)
+        score = tf.nn.softmax(predictions[0])
 
-    return {class_names[i]: float(score[i]) for i in range(3)}
+        return {class_names[i]: float(score[i]) for i in range(3)}
+    except Exception as e:
+        return {"Fehler": str(e)}
 
 # Gradio Interface erstellen
-image_input = gr.inputs.Image(type='pil')
-label_output = gr.outputs.Label(num_top_classes=3)
+image_input = gr.Image(type='pil')
+label_output = gr.Label(num_top_classes=3)
 
 gr.Interface(fn=predict, inputs=image_input, outputs=label_output, 
              title="Pokémon Classifier",