DINHR trained model checkpoints for CryoBench datasets and experimental cryo-EM datasets

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: He, Jiahua, Cheng, Yifan
Format: Recurso digital
Sprache:Englisch
Veröffentlicht: Zenodo 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866901494768336896
author He, Jiahua
Cheng, Yifan
author_facet He, Jiahua
Cheng, Yifan
contents <p>This record provides trained <strong>DINHR</strong> (<strong>D</strong>enoising <strong>I</strong>mplicit <strong>N</strong>eural <strong>H</strong>igh-order <strong>R</strong>epresentation) model checkpoints and auxiliary files to reproduce the results reported in our manuscript. The release includes checkpoints for <em>CryoBench </em>simulated datasets (<em>IgG-1D </em>at multiple SNRs, <em>IgG-RL</em>, <em>TomoTwin-100</em>, <em>Ribosembly</em>) and experimental datasets (<em>EMPIAR-10073</em>, <em>EMPIAR-10076</em>, <em>INO80–Hexasome</em>).<br>Each subfolder contains the released <code>.pt</code> checkpoints (DINHR and INHR baselines where applicable) and dataset-specific auxiliary files (e.g., <code>list_refs.txt</code>, <code>*.npy</code>) used by our evaluation scripts.<br>Code and usage instructions are available in the DINHR GitHub repository.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18447739
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle DINHR trained model checkpoints for CryoBench datasets and experimental cryo-EM datasets
He, Jiahua
Cheng, Yifan
cryo-EM
heterogeneous reconstruction
implicit neural representation
denoising
CryoBench
RELION
cryoSPARC
<p>This record provides trained <strong>DINHR</strong> (<strong>D</strong>enoising <strong>I</strong>mplicit <strong>N</strong>eural <strong>H</strong>igh-order <strong>R</strong>epresentation) model checkpoints and auxiliary files to reproduce the results reported in our manuscript. The release includes checkpoints for <em>CryoBench </em>simulated datasets (<em>IgG-1D </em>at multiple SNRs, <em>IgG-RL</em>, <em>TomoTwin-100</em>, <em>Ribosembly</em>) and experimental datasets (<em>EMPIAR-10073</em>, <em>EMPIAR-10076</em>, <em>INO80–Hexasome</em>).<br>Each subfolder contains the released <code>.pt</code> checkpoints (DINHR and INHR baselines where applicable) and dataset-specific auxiliary files (e.g., <code>list_refs.txt</code>, <code>*.npy</code>) used by our evaluation scripts.<br>Code and usage instructions are available in the DINHR GitHub repository.</p>
title DINHR trained model checkpoints for CryoBench datasets and experimental cryo-EM datasets
topic cryo-EM
heterogeneous reconstruction
implicit neural representation
denoising
CryoBench
RELION
cryoSPARC
url https://doi.org/10.5281/zenodo.18447739