Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from ultralyticsplus import YOLO
+from ultralyticsplus import YOLO, render_result
 from ultralytics.yolo.utils.plotting import Annotator
 
 def yolov8_inference(
@@ -24,23 +24,23 @@ def yolov8_inference(
     model.iou = iou_threshold
     # results = model.predict(image, return_outputs=True)
     results = model.predict(image)
-    object_prediction_list = []
-    annotator = Annotator(image)
-    for _, image_results in enumerate(results):
-        if len(image_results)!=0:
-            image_predictions_in_xyxy_format = image_results['det']
-            for pred in image_predictions_in_xyxy_format:
-                x1, y1, x2, y2 = (
-                    int(pred[0]),
-                    int(pred[1]),
-                    int(pred[2]),
-                    int(pred[3]),
-                )
-                bbox = [x1, y1, x2, y2]
-                score = pred[4]
-                category_name = model.model.names[int(pred[5])]
-                category_id = pred[5]
-                annotator.box_label(bbox, f"{category_name} {score}")
+    # object_prediction_list = []
+    # annotator = Annotator(image)
+    # for _, image_results in enumerate(results):
+    #     if len(image_results)!=0:
+    #         image_predictions_in_xyxy_format = image_results['det']
+    #         for pred in image_predictions_in_xyxy_format:
+    #             x1, y1, x2, y2 = (
+    #                 int(pred[0]),
+    #                 int(pred[1]),
+    #                 int(pred[2]),
+    #                 int(pred[3]),
+    #             )
+    #             bbox = [x1, y1, x2, y2]
+    #             score = pred[4]
+    #             category_name = model.model.names[int(pred[5])]
+    #             category_id = pred[5]
+    #             annotator.box_label(bbox, f"{category_name} {score}")
                 # object_prediction = ObjectPrediction(
                 #     bbox=bbox,
                 #     category_id=int(category_id),
@@ -53,7 +53,9 @@ def yolov8_inference(
     # output_image = visualize_object_predictions(image=image, object_prediction_list=object_prediction_list)
     
     # return output_image['image']
-    return annotator.result()
+    # return annotator.result()
+    render = render_result(model=model, image=image, result=results[0])
+    return render
         
 
 inputs = [