Update app.py

app.py

@@ -1,9 +1,12 @@
 import gradio as gr
 import cv2
+import torch
+
+from sahi.prediction import ObjectPrediction
+from sahi.utils.cv import visualize_object_predictions, read_image
 #import requests
 import os 
-
-from ultralyticsplus import YOLO, render_result
+from ultralyticsplus import YOLO
 
 image_path = [['test_images/2a998cfb0901db5f8210.jpg','linhcuem/chamdiem_yolov8_ver10', 640, 0.25, 0.45],['test_images/2ce19ce0191acb44920b.jpg','linhcuem/chamdiem_yolov8_ver10', 640, 0.25, 0.45],
              ['test_images/2daab6ea3310e14eb801.jpg','linhcuem/chamdiem_yolov8_ver10', 640, 0.25, 0.45], ['test_images/4a137deefb14294a7005 (1).jpg','linhcuem/chamdiem_yolov8_ver10', 640, 0.25, 0.45],
@@ -27,15 +30,37 @@ def yolov8_img_inference(
     iou_threshold: gr.inputs.Slider = 0.45,
 ):
     model = YOLO(model_path)
-    model.overrides['conf'] = conf_threshold
-    model.overrides['iou']= iou_threshold
-    model.overrides['agnostic_nms'] = False  # NMS class-agnostic
-    model.overrides['max_det'] = 1000 
+    model.conf = conf_threshold
+    model.iou= iou_threshold
+    # model.overrides['agnostic_nms'] = False  # NMS class-agnostic
+    # model.overrides['max_det'] = 1000 
     # image = read_image(image)
-    results = model.predict(image)
-    render = render_result(model=model, image=image, result=results[0])
-    
-    return render
+    results = model.predict(image, imgz=image_size, return_outputs=True)
+    object_prediction_list = []
+    for _, image_results in enumerate(results):
+        if len(image_results)!=0:
+            image_prediction_in_xyxy_format = image_results['det']
+            for pred in image_prediction_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]
+                object_prediction = ObjectPrediction(
+                    bbox=bbox,
+                    category_id=int(category_id),
+                    score=score,
+                    category_name=category_name,
+                )
+                object_prediction_list.append(object_prediction)
+    image = read_image(image)
+    output_image = visualize_object_predictions(image=image, object_prediction_list=object_prediction_list)
+    return output_image['image']
 
 inputs_image = [
     gr.inputs.Image(type="filepath", label="Input Image"),