update app

app.py

@@ -10,38 +10,23 @@ model = tf.keras.models.load_model(model_path)
 # Klassenlabels
 labels = ['glioma_tumor', 'meningioma_tumor', 'no_tumor', 'pituitary_tumor']
 
-# Bildvorverarbeitung
-def preprocess_image(image):
-    image = Image.fromarray(image.astype('uint8'))  # Konvertierung des Numpy-Arrays in ein PIL-Bild
-    image = image.resize((224, 224))  # Bildgröße anpassen auf 224x224 Pixel
-    image = np.array(image) / 255 - 1.0  # In Float konvertieren und normalisieren auf [-1, 1]
-
-    # Sicherstellen, dass das Bild 3 Farbkanäle hat
-    if image.ndim == 2:  # Wenn das Bild grau ist, in RGB konvertieren
-        image = np.stack((image,)*3, axis=-1)
-
-    return image
-
-# Vorhersagefunktion
 def predict_image(image):
-    image = preprocess_image(image)  # Verwende die aktualisierte Vorverarbeitung
+    image = Image.fromarray(image.astype('uint8'), 'RGB')
+    image = image.resize((64, 64)) 
+    image = np.array(image)
 
-    # Vorhersage
-    prediction = model.predict(image[None, ...])  # Batch-Dimension hinzufügen
+    prediction = model.predict(np.expand_dims(image, axis=0))
     confidences = {labels[i]: float(prediction[0][i]) for i in range(len(labels))}
     return confidences
 
-# Gradio-Interface
-input_image = gr.Image()
-output_text = gr.Textbox(label="Predicted Value")
-
+# Gradio interface
 iface = gr.Interface(
     fn=predict_image,
-    inputs=input_image, 
-    outputs=gr.Label(),
-    title="Brain Tumor Classification",
-    description="Please upload an image of your MRI brain scan. The model will classify if you've got a tumor or not. Who needs a radiologist anyway?"
+    inputs=gr.Image(),
+    outputs=gr.Label(num_top_classes=10),
+    title="Sentinel Image Classifier",
+    description="Upload your MRI image and the model will predict, if there's a tumor present"
+
 )
 
-# Starten der Gradio-Oberfläche
 iface.launch(share=True)