Training and Validation Datasets for Neural Network to Fill in Missing Data in EBSD Maps

Description

This dataset consists of the synthetic electron backscatter diffraction (EBSD) maps generated for the paper, titled "Hybrid Algorithm for Filling in Missing Data in Electron Backscatter Diffraction Maps" by Emmanuel Atindama, Conor Miller-Lynch, Huston Wilhite, Cody Mattice, Günay Doğan, and Prashant Athavale. The EBSD maps were used to train, test, and validate a neural network algorithm to fill in missing data points in a given EBSD map.The dataset includes 8000 maps for training, 1000 maps for testing, 2000 maps for validation. The dataset also includes noise-added versions of the maps, namely, one more map per each clean map.

Resources

Name Format Description Link
57 validation.zip https://data.nist.gov/od/ds/ark:/88434/mds2-3694/validation.zip
47 https://data.nist.gov/od/ds/ark:/88434/mds2-3694/validation.zip.sha256
57 T-test_data.zip https://data.nist.gov/od/ds/ark:/88434/mds2-3694/T-test_data.zip
47 https://data.nist.gov/od/ds/ark:/88434/mds2-3694/T-test_data.zip.sha256
33 How_the_EBSD_maps_were_generated.pdf https://data.nist.gov/od/ds/mds2-3694/How_the_EBSD_maps_were_generated.pdf
57 training.zip https://data.nist.gov/od/ds/ark:/88434/mds2-3694/training.zip
47 https://data.nist.gov/od/ds/ark:/88434/mds2-3694/training.zip.sha256
57 testing.zip https://data.nist.gov/od/ds/ark:/88434/mds2-3694/testing.zip
47 README.txt https://data.nist.gov/od/ds/mds2-3694/README.txt
47 https://data.nist.gov/od/ds/ark:/88434/mds2-3694/testing.zip.sha256

Tags

  • image-inpainting
  • training-data
  • electron-backscatter-diffusion-ebsd-maps
  • neural-networks

Topics

Categories