YOLO11如何RGB三通道转换为灰色单通道

1. ./ultralytics/cfg/models/v8/yolov8.yaml（也可是你自己修改的yaml文件）文件加 ch：1.

nc: 1 # number of classes
ch: 1

2. 修改 ultralytics/utils/checks.py 文件  （“-”表示删除；“+”表示添加  ；建议保留原代码注释后续方便改回。）

ctrl+f 搜索 ConnectionError

    try:
        from ultralytics import YOLO
-       assert amp_allclose(YOLO("yolov8n.pt"), im)
+       # assert amp_allclose(YOLO("yolo11n.pt"), im)      
        LOGGER.info(f"{prefix}checks passed ✅")
    except ConnectionError:
        LOGGER.warning(
            f"{prefix}checks skipped ⚠️. Offline and unable to download YOLO11n for AMP checks. {warning_msg}"
        )

3. 修改 ultralytics/nn/tasks.py文件 class BaseModel 的 损失函数def loss

 def loss(self, batch, preds=None):
        """
        Compute loss.

        Args:
            batch (dict): Batch to compute loss on
            preds (torch.Tensor | List[torch.Tensor]): Predictions.
        """
        if getattr(self, "criterion", None) is None:
            self.criterion = self.init_criterion()
+       batch['img'] = batch['img'][:,:1,:,:] # ch 3 to 1
        preds = self.forward(batch["img"]) if preds is None else preds
        return self.criterion(preds, batch)

4. 修改 /ultralytics/nn/autobackend.py文件

ctrl+f 搜索 warmup

    def warmup(self, imgsz=(1, 3, 640, 640)):     ----->       def warmup(self, imgsz=(1, 1, 640, 640)):

5. 修改 /ultralytics/engine/validator.py文件 ctrl+f 搜索 warmup

model.warmup(imgsz=(1 if pt else self.args.batch, 3, imgsz, imgsz))
------>    model.warmup(imgsz=(1 if pt else self.args.batch, 1, imgsz, imgsz))

ctrl+f 搜索 dt[1]

 with dt[1]:
+            batch["img"] = batch["img"][:,:1,:,:]
             preds = model(batch["img"], augment=augment)

6.修改 /ultralytics/engine/predictor.py文件

ctrl+f 搜索 warmup

if not self.done_warmup:
-        self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz))
+        self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 1, *self.imgsz))
+        # self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else the dataset.bs, 3, *self.imgsz))        
         self.done_warmup = True

7.修改ultralytics/models/yolo/detect/val.py文件

ctrl+f 搜索 preprocess

     def preprocess(self, batch):
         """Preprocesses batch of images for YOLO training."""
         batch["img"] = batch["img"].to(self.device, non_blocking=True)
         batch["img"] = (batch["img"].half() if self.args.half else batch["img"].float()) / 255
+        batch['img'] = batch['img'][:, :1, :, :]          
         for k in ["batch_idx", "cls", "bboxes"]:
             batch[k] = batch[k].to(self.device)

8.修改ultralytics/engine/predictor.py

ctrl+f 搜索 ascontiguousarray

        not_tensor = not isinstance(im, torch.Tensor)
        if not_tensor:
            im = np.stack(self.pre_transform(im))
            im = im[..., ::-1].transpose((0, 3, 1, 2))  # BGR to RGB, BHWC to BCHW, (n, 3, h, w)
+           im = im[:, :1, :, :]  
            im = np.ascontiguousarray(im)  # contiguous
            im = torch.from_numpy(im)