Update app.py

app.py

@@ -4,7 +4,7 @@ import numpy as np
 from tensorflow.keras.preprocessing import image
 
 # Klassenlabels (ersetzen Sie durch Ihre spezifischen Klassen)
-class_labels = ['Bench Press', 'deadlift', 'hip_thrust', 'lat_pulldown', 'pull_up', 'squat', 'tricep_dips']
+class_labels = ['bench_press', 'deadlift', 'hip_thrust', 'lat_pulldown', 'pull_up', 'squat', 'tricep_dips']
 
 def preprocess(img):
     img = img.resize((150, 150))
@@ -27,14 +27,22 @@ except Exception as e:
     print(f"Error loading ResNet50 model: {e}")
 
 def predict_cnn(img):
-    img_array = preprocess(img)
-    prediction = model_cnn.predict(img_array)
-    return {class_labels[i]: float(prediction[0][i]) for i in range(len(class_labels))}
+    try:
+        img_array = preprocess(img)
+        prediction = model_cnn.predict(img_array)
+        return {class_labels[i]: float(prediction[0][i]) for i in range(len(class_labels))}
+    except Exception as e:
+        print(f"Error in CNN prediction: {e}")
+        return {"error": str(e)}
 
 def predict_resnet50(img):
-    img_array = preprocess(img)
-    prediction = model_resnet50.predict(img_array)
-    return {class_labels[i]: float(prediction[0][i]) for i in range(len(class_labels))}
+    try:
+        img_array = preprocess(img)
+        prediction = model_resnet50.predict(img_array)
+        return {class_labels[i]: float(prediction[0][i]) for i in range(len(class_labels))}
+    except Exception as e:
+        print(f"Error in ResNet50 prediction: {e}")
+        return {"error": str(e)}
 
 # Gradio Interface für das CNN Modell
 interface_cnn = gr.Interface(