Update app.py

app.py

@@ -15,21 +15,19 @@ def normalize_image(img):
     return img
 
 def predict_top_classes(img, num_top_classes=5):
-    img = img.convert('RGB')
-    img_data = normalize_image(img)
-    x = np.array(img_data)
-    x = np.expand_dims(x, axis=0)
-    temp = model.predict(x)
-
-    top_class_indices = np.argpartition(temp, -num_top_classes)[-num_top_classes:]
-    top_class_indices = top_class_indices[np.argsort(temp[0, top_class_indices])[::-1]]
-
-    top_classes = [CLASS_LABEL[i] for i in top_class_indices]
-    top_probabilities = [temp[0, i] for i in top_class_indices]
-
-    return dict(zip(top_classes, top_probabilities))
-
+     img = img.convert('RGB')
+     img_data = _normalize_img(img)
+     x = np.array(img_data)
+     x = np.expand_dims(x, axis=0)
+     temp = model.predict(x)
+     
+     idx = np.argsort(np.squeeze(temp))[::-1]
+     top5_value = np.asarray([temp[0][i] for i in idx[0:5]])
+     top5_idx = idx[0:5]
+     
+     return {CLASS_LABEL[i]:str(v) for i,v in zip(top5_idx,top5_value)}
+    
 model = tf.keras.models.load_model("Xception.h5")
 
-interface = gr.Interface(predict_top_classes, gr.inputs.Image(type='pil'), outputs='json', args={'num_top_classes': 5})
+interface = gr.Interface(predict_top_classes, gr.inputs.Image(type='pil'), outputs='label', args={'num_top_classes': 5})
 interface.launch()