Non-normalized or out of bounds coordinates

Community Help
,
1
  • Setup:
    I ran the code using Google Colab with GPU, I’m using the yolov8n-seg.pt architecture and the ultralytics library in its most up-to-date version.

Even exporting the database as YOLOv8 Oriented Bouding Boxes is not working, I would like guidance. Here is the link to the dataset:

Sign in to Roboflow.

  • Result obtained in Colab

train: Scanning /content/drive/MyDrive/YOLO_CROP_NONCROP/train/labels.cache… 8 images, 0 backgrounds, 8 corrupt: 100%|██████████| 8/8 [00:00<?, ?it/s]train: WARNING :warning: /content/drive/MyDrive/YOLO_CROP_NONCROP/train/images/marcelo_vincenzi_mt-5105580-01b_ndvi_01-07-2019_raw_png.rf.239a8a9f2c761970de88fb979db4e66c.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.3749 1.3064 1.0743]
train: WARNING :warning: /content/drive/MyDrive/YOLO_CROP_NONCROP/train/images/marcelo_vincenzi_mt-5105580-01b_ndvi_02-05-2019_raw_png.rf.95abed423682da2c786b9f56534fdcf8.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.3738 1.3042]
train: WARNING :warning: /content/drive/MyDrive/YOLO_CROP_NONCROP/train/images/marcelo_vincenzi_mt-5105580-01b_ndvi_02-12-2023_raw_png.rf.648920853fc528a7f7b16f3bc0f0fa59.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.3382 1.2367 1.0636]
train: WARNING :warning: /content/drive/MyDrive/YOLO_CROP_NONCROP/train/images/marcelo_vincenzi_mt-5105580-01b_ndvi_03-09-2023_raw_png.rf.3080b7d2a33dce8d87d5efededeaec9f.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.3262 1.2115 1.1008]
train: WARNING :warning: /content/drive/MyDrive/YOLO_CROP_NONCROP/train/images/marcelo_vincenzi_mt-5105580-01b_ndvi_03-10-2021_raw_png.rf.e7ca76bbe4364f91bc1ae50ed450a3de.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0857 1.3726 1.3021 1.0066]
train: WARNING :warning: /content/drive/MyDrive/YOLO_CROP_NONCROP/train/images/marcelo_vincenzi_mt-5105580-01b_ndvi_04-08-2020_raw_png.rf.fedcbcaab0f256746c35b116ed517e80.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.3055 1.1734 1.1093]
train: WARNING :warning: /content/drive/MyDrive/YOLO_CROP_NONCROP/train/images/marcelo_vincenzi_mt-5105580-01b_ndvi_04-08-2021_raw_png.rf.6a3dd90cea9868270e10322fc2ac8bda.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.3416 1.2434 1.0104]
train: WARNING :warning: /content/drive/MyDrive/YOLO_CROP_NONCROP/train/images/marcelo_vincenzi_mt-5105580-01b_ndvi_04-08-2022_raw_png.rf.ac3d5708600b7515dd9dc537e4013e3f.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.3475 1.2545 1.0766]
WARNING :warning: No images found in /content/drive/MyDrive/YOLO_CROP_NONCROP/train/labels.cache, training may not work correctly. See Object Detection Datasets Overview - Ultralytics YOLOv8 Docs for dataset formatting guidance.

ValueError Traceback (most recent call last)
in <cell line: 8>()
6
7 # Train the model on the COCO8 example dataset for 100 epochs
----> 8 results = model.train(data=‘/content/drive/MyDrive/YOLO_CROP_NONCROP/v7/data.yaml’, epochs=100, imgsz=640)

9 frames
/usr/local/lib/python3.10/dist-packages/ultralytics/data/dataset.py in get_labels(self)
159 # Check if the dataset is all boxes or all segments
160 lengths = ((len(lb[“cls”]), len(lb[“bboxes”]), len(lb[“segments”])) for lb in labels)
→ 161 len_cls, len_boxes, len_segments = (sum(x) for x in zip(*lengths))
162 if len_segments and len_boxes != len_segments:
163 LOGGER.warning(

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

2

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.