Add reco for gradio

app.py

@@ -133,7 +133,8 @@ def detect_logo(img, model, confidence):
                 for *xyxy, conf, cls in reversed(det):
                     name_class = names[int(cls.item())]
                     all_classes_detected.append(name_class)
-                    all_recommendations.append(recommender.make_recommendation(name_class))
+                    name_recommanded = recommender.make_recommendation(name_class)
+                    all_recommendations.append(name_recommanded)
                     if save_txt:
                         xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()
                         line = (names[int(cls.item())], *xywh, conf) if opt.save_conf else (names[int(cls.item())], *xywh)
@@ -142,7 +143,7 @@ def detect_logo(img, model, confidence):
                             f.write(('%g ' * (len(line)-1)).rstrip() % line[1:] + '\n')
 
                     if save_img or view_img:
-                        label = f'{names[int(cls)]} {conf:.2f}'
+                        label = f'{names[int(cls)]} {conf:.2f} || Recommendation : {name_recommanded.lower()}'
                         plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
             if view_img:
                 cv2.imshow(str(p), im0)

detect.py

@@ -13,9 +13,11 @@ from utils.general import check_img_size, check_requirements, check_imshow, non_
     scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
 from utils.plots import plot_one_box
 from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel
+from recommendation import SimilarityRecommender
 
 
 def detect(save_img=False):
+    recommender = SimilarityRecommender("./TopBrands.xlsx")
     source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace
     save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
     webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
@@ -117,6 +119,8 @@ def detect(save_img=False):
 
                 # Write results
                 for *xyxy, conf, cls in reversed(det):
+                    name_class = names[int(cls.item())]
+                    name_recommanded = recommender.make_recommendation(name_class)
                     if save_txt:  # Write to file
                         xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                         line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)  # label format
@@ -124,7 +128,7 @@ def detect(save_img=False):
                             f.write(('%g ' * len(line)).rstrip() % line + '\n')
 
                     if save_img or view_img:  # Add bbox to image
-                        label = f'{names[int(cls)]} {conf:.2f}'
+                        label = f'{names[int(cls)]} {conf:.2f} || Recommendation : {name_recommanded.lower()}'
                         plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=1)
 
             # Print time (inference + NMS)

hubconf.py

@@ -83,7 +83,7 @@ def yolov7(pretrained=True, channels=3, classes=80, autoshape=True):
 
 
 if __name__ == '__main__':
-    model = custom(path_or_model='yolov7.pt')  # custom example
+    model = custom(path_or_model='best_logo.pt')  # custom example
     # model = create(name='yolov7', pretrained=True, channels=3, classes=80, autoshape=True)  # pretrained example
 
     # Verify inference