YOLO Darknet dataset not compatible with YOLOv8

[johnlockejrr]

I want to train a segmentation model on YOLOv8. My dataset/labels are Darknet format:

0 0.7265248796147672 0.1669776119402985 0.5453451043338684 0.025497512437810944
0 0.7259229534510433 0.18734452736318408 0.5457463884430177 0.023320895522388058
0 0.7251203852327448 0.20413557213930347 0.5481540930979133 0.02394278606965174
0 0.7265248796147672 0.22046019900497513 0.5453451043338684 0.025497512437810944
0 0.7269261637239165 0.23958333333333334 0.5445425361155698 0.02269900497512438
0 0.726123595505618 0.2583955223880597 0.5461476725521669 0.021766169154228854
0 0.7259229534510433 0.2745646766169154 0.5465489566613162 0.0236318407960199
0 0.7259229534510433 0.3081467661691542 0.5465489566613162 0.026741293532338308
0 0.726123595505618 0.3277363184079602 0.5461476725521669 0.025497512437810944
0 0.7255216693418941 0.345615671641791 0.5473515248796148 0.02269900497512438

Should I convert (if so, how?) to other format?

My dataset YAML file:
path: sam_v2

test: test.txt
train: train.txt
val: val.txt

names:
  0: text_line

Sample of test.txt

/home/incognito/yolov8/datasets/sam_v2/images/01429057-33c7-5572-be4f-aba1aafe4ddf.jpg
/home/incognito/yolov8/datasets/sam_v2/images/a34e234a-76be-5392-9b39-4abdcd051719.jpg
/home/incognito/yolov8/datasets/sam_v2/images/ecf7dc5c-3802-5177-82e4-4a232094b43f.jpg

I get this error:

Starting training for 100 epochs...

      Epoch    GPU_mem   box_loss   seg_loss   cls_loss   dfl_loss  Instances       Size
  0%|          | 0/2 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "/home/incognito/yolov8/yolo-py3.11/lib/python3.11/site-packages/ultralytics/utils/loss.py", line 290, in __call__
    targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 1289 but got size 0 for tensor number 1 in the list.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/incognito/yolov8/train_yv8.py", line 15, in <module>
    results = model.train(data="seg_2.yaml", epochs=100, imgsz=640, patience=50, batch=-1, save=True) # build from YAML and transfer weights
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/incognito/yolov8/yolo-py3.11/lib/python3.11/site-packages/ultralytics/engine/model.py", line 815, in train
    self.trainer.train()
  File "/home/incognito/yolov8/yolo-py3.11/lib/python3.11/site-packages/ultralytics/engine/trainer.py", line 208, in train
    self._do_train(world_size)
  File "/home/incognito/yolov8/yolo-py3.11/lib/python3.11/site-packages/ultralytics/engine/trainer.py", line 386, in _do_train
    self.loss, self.loss_items = self.model(batch)
                                 ^^^^^^^^^^^^^^^^^
  File "/home/incognito/yolov8/yolo-py3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/incognito/yolov8/yolo-py3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/incognito/yolov8/yolo-py3.11/lib/python3.11/site-packages/ultralytics/nn/tasks.py", line 105, in forward
    return self.loss(x, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/incognito/yolov8/yolo-py3.11/lib/python3.11/site-packages/ultralytics/nn/tasks.py", line 287, in loss
    return self.criterion(preds, batch)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/incognito/yolov8/yolo-py3.11/lib/python3.11/site-packages/ultralytics/utils/loss.py", line 295, in __call__
    raise TypeError(
TypeError: ERROR ❌ segment dataset incorrectly formatted or not a segment dataset.
This error can occur when incorrectly training a 'segment' model on a 'detect' dataset, i.e. 'yolo train model=yolov8n-seg.pt data=coco8.yaml'.
Verify your dataset is a correctly formatted 'segment' dataset using 'data=coco8-seg.yaml' as an example.
See https://docs.ultralytics.com/datasets/segment/ for help.

[glenn-jocher]

@johnlockejrr to train a segmentation model with YOLOv8, you'll need to convert your Darknet format labels to the Ultralytics YOLO format. Ensure each label file includes class indices and segmentation mask coordinates. You can use the convert_coco function if your data is in COCO format. For more details, refer to the Ultralytics documentation.