Update README.md

README.md

@@ -69,13 +69,13 @@ import PIL.Image
 def predict(image_path, weights='ultima_yolov9-e.pt', imgsz=640, conf_thres=0.1, iou_thres=0.45):
     # Initialize
     device = select_device('0')
-    model = DetectMultiBackend(weights=weights, device="0", fp16=False, data='data/coco.yaml')
+    model = DetectMultiBackend(weights=weights, device=device, fp16=False)
     stride, names, pt = model.stride, model.names, model.pt
 
     # Load image
-    image = np.array(PIL.Image.open(image_path))
-    img = letterbox(img0, imgsz, stride=stride, auto=True)[0]
-    img = img[:, :, ::-1].transpose(2, 0, 1)
+    image = np.array(PIL.Image.open(image_path).convert("RGB"))
+    img = letterbox(image, imgsz, stride=stride, auto=True)[0]
+    img = img.transpose(2, 0, 1)
     img = np.ascontiguousarray(img)
     img = torch.from_numpy(img).to(device).float()
     img /= 255.0
@@ -88,10 +88,10 @@ def predict(image_path, weights='ultima_yolov9-e.pt', imgsz=640, conf_thres=0.1,
     # Apply NMS
     pred = non_max_suppression(pred[0][0], conf_thres, iou_thres, classes=None, max_det=1000)
 ```
-or use `detect_dual.py` in yolov9 repo.
+or use `detect.py` in yolov9 repo.
 
 ```bash
-python ./detect_dual.py --source [image_path] --device 0 --img 1280 --weights './ultima_yolov9.pt' --name ultima_yolov9_1280_detect
+python ./detect.py --source [image_path] --device 0 --img 1280 --weights './ultima_yolov9-e.pt' --name ultima_yolov9_1280_detect
 ```
 
 # Training Infomation