resisc45.md

resisc45

Warning: Manual download required. See instructions below.

• Description:

RESISC45 dataset is a publicly available benchmark for Remote Sensing Image Scene Classification (RESISC), created by Northwestern Polytechnical University (NWPU). This dataset contains 31,500 images, covering 45 scene classes with 700 images in each class.

• Additional Documentation: Explore on Papers With Code north_east

• Homepage: http://www.escience.cn/people/JunweiHan/NWPU-RESISC45.html

• Source code: tfds.datasets.resisc45.Builder

• Versions:

  • 3.0.0 (default): No release notes.

• Download size: Unknown size

• Dataset size: 407.97 MiB

• Manual download instructions: This dataset requires you to download the source data manually into download_config.manual_dir (defaults to ~/tensorflow_datasets/downloads/manual/):
  Dataset can be downloaded from OneDrive: https://1drv.ms/u/s!AmgKYzARBl5ca3HNaHIlzp_IXjs After downloading the rar file, please extract it to the manual_dir.

• Auto-cached (documentation): No

• Splits:

Split	Examples
'train'	31,500

• Feature structure:

FeaturesDict({
    'filename': Text(shape=(), dtype=string),
    'image': Image(shape=(256, 256, 3), dtype=uint8),
    'label': ClassLabel(shape=(), dtype=int64, num_classes=45),
})

• Feature documentation:

Feature	Class	Shape	Dtype	Description

     | FeaturesDict |               |        |

filename | Text | | string | image | Image | (256, 256, 3) | uint8 | label | ClassLabel | | int64 |

• Supervised keys (See as_supervised doc): ('image', 'label')

• Figure (tfds.show_examples):

• Examples (tfds.as_dataframe):

{% framebox %}

Display examples...

<script> const url = "https://storage.googleapis.com/tfds-data/visualization/dataframe/resisc45-3.0.0.html"; const dataButton = document.getElementById('displaydataframe'); dataButton.addEventListener('click', async () => { // Disable the button after clicking (dataframe loaded only once). dataButton.disabled = true;

const contentPane = document.getElementById('dataframecontent'); try { const response = await fetch(url); // Error response codes don't throw an error, so force an error to show // the error message. if (!response.ok) throw Error(response.statusText);

const data = await response.text();
contentPane.innerHTML = data;

} catch (e) { contentPane.innerHTML = 'Error loading examples. If the error persist, please open ' + 'a new issue.'; } }); </script>

{% endframebox %}

• Citation:

@article{Cheng_2017,
   title={Remote Sensing Image Scene Classification: Benchmark and State of the Art},
   volume={105},
   ISSN={1558-2256},
   url={http://dx.doi.org/10.1109/JPROC.2017.2675998},
   DOI={10.1109/jproc.2017.2675998},
   number={10},
   journal={Proceedings of the IEEE},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Cheng, Gong and Han, Junwei and Lu, Xiaoqiang},
   year={2017},
   month={Oct},
   pages={1865-1883}
}