Supervisely Potatoes Dataset for Crops and Weed Segmentation is a dataset for instance segmentation, semantic segmentation, and object detection tasks. Possible applications of the dataset could be in the agricultural industry.

The dataset consists of 1055 images with 3971 labeled objects belonging to 2 different classes including crop and weed.

Images in the Supervisely Potatoes dataset have pixel-level instance segmentation annotations. Due to the nature of the instance segmentation task, it can be automatically transformed into a semantic segmentation (only one mask for every class) or object detection (bounding boxes for every object) tasks. There are 82 (8% of the total) unlabeled images (i.e. without annotations). There is 1 split in the dataset: train (1055 images). Alternatively, the dataset could be split into 3 field IDs: 113 (935 images), 114 (60 images), and 116 (60 images). The dataset was released in 2023 by the Supervisely.

Here is the visualized example grid with animated annotations:

Supervisely Potatoes Dataset for Crops and Weed Segmentation is under CC BY-NC-SA 4.0 license.

Source

If you make use of the Supervisely Potatoes data, please cite the following reference:

@dataset{Supervisely Potatoes,
  author={Supervisely},
  title={Supervisely Potatoes Dataset for Crops and Weed Segmentation},
  year={2023},
  url={https://supervisely.com/blog/train-a-model-with-62-labeled-images-hrda-semi-supervised/}
}

Source

Dataset Supervisely Potatoes can be downloaded in Supervisely format:

As an alternative, it can be downloaded with dataset-tools package:

pip install --upgrade dataset-tools

… using following python code:

import dataset_tools as dtools

dtools.download(dataset='Supervisely Potatoes', dst_dir='~/dataset-ninja/')

Make sure not to overlook the python code example available on the Supervisely Developer Portal. It will give you a clear idea of how to effortlessly work with the downloaded dataset.

The data in original format can be downloaded here.