Lincolnbeet Dataset

Estimated reading: 3 minutes

Visualization of the LincolnBeet Dataset in the Deep Lake UI

LincoInBeet dataset

What is LincolnBeet Dataset?

The Lincolnbeet dataset includes 4402 images (1920 x 1080 pixels) containing weed, plants, and sugar beets, as well as object detection labels. The labels are provided in COCOjson, XML, and darknet formats. The Lincolnbeet dataset is an object detection dataset created to facilitate the development of methods to identify objects in an environment with a high level of occlusion. In addition, the dataset was introduced to encourage the evaluation of various object detection models in practice.

Download LincolnBeet Dataset in Python

Instead of downloading the LincolnBeet, you can effortlessly load it in Python via our open-source package Deep Lake with just one line of code

Load LincolnBeet Train Subset

				
					import deeplake
ds = deeplake.load('hub://activeloop/lincolnbeet-train')

Load LincolnBeet Validation Subset

				
					import deeplake
ds = deeplake.load('hub://activeloop/lincolnbeet-val')

Load LincolnBeet Test Subset

				
					import deeplake
ds = deeplake.load('hub://activeloop/lincolnbeet-test')

LincolnBeet Dataset Structure

Data Fields

image: a tensor containing 1920 x 1080 pixel images.
boxes: a tensor to draw bounding boxes around weed and sugar beet.
labels: a class label tensor classifying object as “weed” or “sugar_beet”.

Data Splits

LincolnBeet training split comprises 3080 images.
LincolnBeet testing split comprises 880 images.
LincolnBeet validation split comprises 440 images.

Dataset Characteristics

Number of identified objects: 39246
- Total number of Sugar Beet Identified: 16399
- Total Weed Plants identified: 22847
The average percentage of the bounding box that is occluded is 0.0176
The average area of the image occupied by bounding boxes is 0.0717

How to use LincolnBeet Dataset with PyTorch and TensorFlow in Python

Training LincolnBeet dataset with PyTorch in Python

Let’s use Deep Lake built-in PyTorch one-line dataloader to connect the data to the compute:

				
					dataloader = ds.pytorch(num_workers=0, batch_size=4, shuffle=False)

Training LincolnBeet with TensorFlow in Python

				
					dataloader = ds.tensorflow()

Additional Information

Repository: https://github.com/LAR/lincolnbeet_dataset
Paper: Salazar-Gomez, A., Darbyshire, M., Gao, J., Sklar, E. I., & Parsons, S. (2021). Towards practical object detection for weed spraying in precision agriculture. arXiv preprint arXiv:2109.11048.
Point of Contact: [email protected]

Dataset Curators

Salazar-Gomez, Adrian and Darbyshire, Madeleine and Gao, Junfeng and Sklar, Elizabeth I and Parsons, Simon

Licensing Information

Deep Lake users may have access to a variety of publicly available datasets. We do not host or distribute these datasets, vouch for their quality or fairness, or claim that you have a license to use the datasets. It is your responsibility to determine whether you have permission to use the datasets under their license.

If you’re a dataset owner and do not want your dataset to be included in this library, please get in touch through a GitHub issue. Thank you for your contribution to the ML community!

Citation Information

				
					@article{salazar2021towards,
  title={Towards practical object detection for weed spraying 
  in precision agriculture},
  author={Salazar-Gomez, Adrian and Darbyshire, Madeleine and Gao, 
  Junfeng and Sklar, Elizabeth I and Parsons, Simon},
  journal={arXiv preprint arXiv:2109.11048},
  year={2021}
}