Yolo 11 nano dataset structured incorrectly

Question

I'm new to working with Yolo and trying for the first time to structure my database. This is how my directory is structured.

 Project_Name/
├── datasets/
│   ├── images/
│   │   ├── train/               
│   │   └── val/                 
│   ├── labels/
│   │   ├── train/               
│   │   │   ├── 000000000009.txt
│   │   │   ├── 000000000025.txt
│   │   │   ├── 000000000034.txt
│   │   └── val/                 
│   │       ├── 000000000030.txt
│   │   └── train.cache          
├── raw_set/
│   ├── images/                  # Data which i separate into test and val
│   └── labels/                  
├── gate.yaml                    
├── runs/                        
├── pat.txt                      
├── YOLO_Project_name.ipynb       
└── yolo11n.pt 

When I run the following cell in YOLO_Project_name.ipynb:

model = YOLO("yolo11n.pt")
results = model.train(data="datasets/gate.yaml", epochs=5, imgsz=640, device="mps")

I get the following error.

Error Message

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[58], line 2
      1 model = YOLO("yolo11n.pt")
----> 2 results = model.train(data="datasets/gate.yaml", epochs=5, imgsz=640, device="mps")

File ~/Library/Python/3.11/lib/python/site-packages/ultralytics/engine/model.py:802, in Model.train(self, trainer, **kwargs)
    799     self.model = self.trainer.model
    801 self.trainer.hub_session = self.session  # attach optional HUB session
--> 802 self.trainer.train()
    803 # Update model and cfg after training
    804 if RANK in {-1, 0}:

File ~/Library/Python/3.11/lib/python/site-packages/ultralytics/engine/trainer.py:207, in BaseTrainer.train(self)
    204         ddp_cleanup(self, str(file))
    206 else:
--> 207     self._do_train(world_size)

File ~/Library/Python/3.11/lib/python/site-packages/ultralytics/engine/trainer.py:327, in BaseTrainer._do_train(self, world_size)
    325 if world_size > 1:
    326     self._setup_ddp(world_size)
--> 327 self._setup_train(world_size)
    329 nb = len(self.train_loader)  # number of batches
    330 nw = max(round(self.args.warmup_epochs * nb), 100) if self.args.warmup_epochs > 0 else -1  # warmup iterations
...
    165         f"len(boxes) = {len_boxes}. To resolve this only boxes will be used and all segments will be removed. "
    166         "To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset."
    167     )

ValueError: not enough values to unpack (expected 3, got 0)

Where am I going wrong here, what does this error message mean? The project is meant to identify objects of a single class (not one the model was pre-trained on) and locate it within the frame.

Answer 1

I think there is something wrong with your yaml file.Can you show what it looks like? it should be something like below:

path: /home/user/Projects/deep/yolo-torch-2/yolov8 # dataset root dir
train: images/train # train images (relative to 'path')
val: images/val # val images (relative to 'path') 
test: # test images (optional)

# Classes
names:
  0: class1
  1: class2
  2: class3
  3: class4