DOE CODE   /    Search Results   /    NEURAL NETWORK FOR COHERENT DIFFRACTION IMAGE INVERSION

NEURAL NETWORK FOR COHERENT DIFFRACTION IMAGE INVERSION

RESOURCE

Publicly Accessible Repository
https://github.com/hyiprc/3D-CDI-NN
https://doi.org/10.11578/dc.20210819.7

SAVE / SHARE



ANL Badge

Abstract

A deep neural network model plus automatic differentiation is developed for retrieving phase information from 3D coherent diffraction images. The model is implemented using Tensorflow and the training dataset is generated using physics-based atomistic simulations. Custom codes are written to handle the resampling of diffraction images to oversampling ratios appropriate for the neural network model.
Developers:
Release Date:
2021-04-30
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Licenses:
BSD 3-clause "New" or "Revised" License
Sponsoring Org.:
Code ID:
62502
Research Org.:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Country of Origin:
United States

RESOURCE

Publicly Accessible Repository
https://github.com/hyiprc/3D-CDI-NN
https://doi.org/10.11578/dc.20210819.7

SAVE / SHARE



ANL Badge

Citation Formats

CHAN, HENRY, CHERUKARA, MATHEW J., and HARDER, ROSS J. NEURAL NETWORK FOR COHERENT DIFFRACTION IMAGE INVERSION. Computer Software. https://github.com/hyiprc/3D-CDI-NN. US DOE BES ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING, ARGONNE LDRD. 30 Apr. 2021. Web. doi:10.11578/dc.20210819.7.
CHAN, HENRY, CHERUKARA, MATHEW J., & HARDER, ROSS J. (2021, April 30). NEURAL NETWORK FOR COHERENT DIFFRACTION IMAGE INVERSION. [Computer software]. https://github.com/hyiprc/3D-CDI-NN. https://doi.org/10.11578/dc.20210819.7.
CHAN, HENRY, CHERUKARA, MATHEW J., and HARDER, ROSS J. "NEURAL NETWORK FOR COHERENT DIFFRACTION IMAGE INVERSION." Computer software. April 30, 2021. https://github.com/hyiprc/3D-CDI-NN. https://doi.org/10.11578/dc.20210819.7.
@misc{ doecode_62502,
title = {NEURAL NETWORK FOR COHERENT DIFFRACTION IMAGE INVERSION},
author = {CHAN, HENRY and CHERUKARA, MATHEW J. and HARDER, ROSS J.},
abstractNote = {A deep neural network model plus automatic differentiation is developed for retrieving phase information from 3D coherent diffraction images. The model is implemented using Tensorflow and the training dataset is generated using physics-based atomistic simulations. Custom codes are written to handle the resampling of diffraction images to oversampling ratios appropriate for the neural network model.},
doi = {10.11578/dc.20210819.7},
url = {https://doi.org/10.11578/dc.20210819.7},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20210819.7}},
year = {2021},
month = {apr}
}