v2.5.0
Datasets ⭐
EXAMPLE CODE
GlaS Dataset
Load the GlaS dataset in Python with one line of code. 165 images made of benign malignant glands. Stream GlaS while training models in PyTorch & TensorFlow.
Visualization of the GlaS Train Dataset on the Activeloop Platform

GlaS dataset

What is GlaS Dataset?

The GlaS (Gland Segmentation) Dataset is created to encourage research in gland segmentation algorithms on images of hematoxylin and Eosin (H&E) stained slides (consists of a variety of histologic grades). The dataset ground truth annotations have been annotated by expert pathologists. There are 37 benign and 48 malignant training images. The testing dataset contains 37 benign and 43 malignant images. In total, the dataset contains 165 images.

Download GlaS Dataset in Python

Instead of downloading the GlaS dataset in Python, you can effortlessly load it in Python via our open-source package Hub with just one line of code.

Load GlaS Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/glas-train")
Copied!

Load GlaS Dataset Testing Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/glas-test")
Copied!

GlaS Dataset Structure

GlaS Data Fields

  • images: tensor containing images of the hematoxylin and Eosin (H&E) stained slides
  • masks: tensor containing segmented area of their respective images
  • grade_Glas: tensor containing labels of cancer type
  • grade_Sirinukunwattana: tensor containing labels of patient health patient_ids: tensor containing patient ids

How to use GlaS Dataset with PyTorch and TensorFlow in Python

Train a model on GlaS dataset with PyTorch in Python

Let's use Hub's built-in PyTorch one-line dataloader to connect the data to the compute:
1
dataloader = ds.pytorch(num_workers=0, batch_size=4, shuffle=False)
Copied!

Train a model on GlaS dataset with TensorFlow in Python

1
dataloader = ds.tensorflow()
Copied!

Additional Information about GlaS Dataset

GlaS Dataset Description

GlaS Dataset Curators

Sirinukunwattana, Korsuk, David RJ Snead, and Nasir M. Rajpoot.

GlaS Dataset Licensing Information

Hub 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!

GlaS Dataset Citation Information

1
@article{sirinukunwattana2015stochastic,
2
title={A stochastic polygons model for glandular structures in colon histology images},
3
author={Sirinukunwattana, Korsuk and Snead, David RJ and Rajpoot, Nasir M},
4
journal={IEEE transactions on medical imaging},
5
volume={34},
6
number={11},
7
pages={2366--2378},
8
year={2015},
9
publisher={IEEE}
10
}
Copied!