Skip to content

HUB Datasets

1. Upload a Dataset

Ultralytics HUB datasets are just like YOLOv5 and YOLOv8 🚀 datasets, they use the same structure and the same label formats to keep everything simple.

When you upload a dataset to Ultralytics HUB, make sure to place your dataset YAML inside the dataset root directory as in the example shown below, and then zip for upload to Your dataset YAML, directory and zip should all share the same name. For example, if your dataset is called 'coco8' as in our example ultralytics/hub/example_datasets/, then you should have a coco8.yaml inside your coco8/ directory, which should zip to create for upload:

zip -r coco8

The example_datasets/ dataset in this repository can be downloaded and unzipped to see exactly how to structure your custom dataset.

The dataset YAML is the same standard YOLOv5 and YOLOv8 YAML format. See the YOLOv5 and YOLOv8 Train Custom Data tutorial for full details.

# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path:  # dataset root dir (leave empty for HUB)
train: images/train  # train images (relative to 'path') 8 images
val: images/val  # val images (relative to 'path') 8 images
test:  # test images (optional)

# Classes
  0: person
  1: bicycle
  2: car
  3: motorcycle

After zipping your dataset, sign in to Ultralytics HUB and click the Datasets tab. Click 'Upload Dataset' to upload, scan and visualize your new dataset before training new YOLOv5 or YOLOv8 models on it!

HUB Dataset Upload

Created 2023-05-06, Updated 2023-05-09
Authors: Glenn Jocher (3)