Update app.py

app.py

@@ -2,29 +2,29 @@ import gradio as gr
 from PIL import Image
 import numpy as np
 from tensorflow.keras.preprocessing import image as keras_image
-from tensorflow.keras.applications.resnet50 import preprocess_input
+from tensorflow.keras.applications.inception_v3 import preprocess_input
 from tensorflow.keras.models import load_model
 
-# Load your trained model
-model = load_model('/home/user/app/one_piece_character_classifier.h5')  # Ensure this path is correct
+# Lade dein trainiertes Modell
+model = load_model('/home/user/app/one_piece_character_classifier.h5')  # Stelle sicher, dass dieser Pfad korrekt ist
 
-def predict_pokemon(img):
-    img = Image.fromarray(img.astype('uint8'), 'RGB')  # Ensure the image is in RGB
-    img = img.resize((224, 224))  # Resize the image properly using PIL
-    img_array = keras_image.img_to_array(img)  # Convert the image to an array
-    img_array = np.expand_dims(img_array, axis=0)  # Expand dimensions to fit model input
-    img_array = preprocess_input(img_array)  # Preprocess the input as expected by ResNet50
+def predict_character(img):
+    img = Image.fromarray(img.astype('uint8'), 'RGB')  # Stelle sicher, dass das Bild im RGB-Format vorliegt
+    img = img.resize((299, 299))  # Größe des Bildes anpassen für InceptionV3
+    img_array = keras_image.img_to_array(img)  # Bild in ein Array umwandeln
+    img_array = np.expand_dims(img_array, axis=0)  # Dimensionen erweitern, um dem Model-Input zu entsprechen
+    img_array = preprocess_input(img_array)  # Input für InceptionV3 vorverarbeiten
     
-    prediction = model.predict(img_array)  # Predict using the model
-    classes = ['Brook', 'Chopper', 'Zoro' ]  # Specific Pokémon names
-    return {classes[i]: float(prediction[0][i]) for i in range(3)}  # Return the prediction
+    prediction = model.predict(img_array)  # Vorhersage mit dem Modell
+    classes = ['Brook', 'Chopper', 'Zoro']  # Spezifische Charakter-Namen
+    return {classes[i]: float(prediction[0][i]) for i in range(3)}  # Vorhersage zurückgeben
 
-# Define Gradio interface
-interface = gr.Interface(fn=predict_pokemon, 
-                         inputs="image",  # Simplified input type
-                         outputs="label",  # Simplified output type
+# Definiere das Gradio-Interface
+interface = gr.Interface(fn=predict_character, 
+                         inputs="image",  # Vereinfachter Eingabetyp
+                         outputs="label",  # Vereinfachter Ausgabetyp
                          title="One Piece Classifier",
-                         description="Upload an image of a OP Character and the classifier will predict its name.")
+                         description="Lade ein Bild eines OP-Charakters hoch und der Klassifikator wird den Namen vorhersagen.")
 
-# Launch the interface
-interface.launch()
+# Starte das Interface
+interface.launch()