Update app.py

app.py

@@ -4,7 +4,7 @@ import numpy as np
 from PIL import Image
 
 
-model_path = "BMWXModelClassifier.keras"
+model_path = "DogClassifier.keras"
 model = tf.keras.models.load_model(model_path)
 
 # Define the core prediction function
@@ -23,15 +23,14 @@ def predict_bmwX(image):
     prediction = tf.nn.softmax(prediction)
     
     # Create a dictionary with the probabilities for each Pokemon
-    x1 = np.round(float(prediction[0][0]), 2)
-    x2 = np.round(float(prediction[0][1]), 2)
-    x3 = np.round(float(prediction[0][2]), 2)
-    x4 = np.round(float(prediction[0][3]), 2)
-    x5 = np.round(float(prediction[0][4]), 2)
-    x6 = np.round(float(prediction[0][5]), 2)
-    x7 = np.round(float(prediction[0][6]), 2)
-    
-    return {'X1': x1, 'X2': x2, 'X3': x3, 'X4': x4, 'X5': x5, 'X6': x6, 'X7': x7}
+    borderCollie = np.round(float(prediction[0][0]), 2)
+    corgi = np.round(float(prediction[0][1]), 2)
+    germanShepard = np.round(float(prediction[0][2]), 2)
+    goldenRetriever = np.round(float(prediction[0][3]), 2)
+    pitBull = np.round(float(prediction[0][4]), 2)
+    rottweiler = np.round(float(prediction[0][4]), 2)
+        
+    return {'Border Collie': borderCollie, 'Corgi': corgi, 'German Shepard': germanShepard, 'Golder Retriver': goldenRetriever, 'Pit Bull': pitBull, 'Rottweiler': rottweiler}
 
 
 input_image = gr.Image()