datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
fno-predictions
PDEBench FNO Re-evaluation: Prediction Tensors
Test-set prediction arrays from The Unrealized Potential of Fourier Neural Operators: A Systematic Re-evaluation of PDEBench Baselines (NeurIPS 2026 E&D Track submission).
File layout
For all standard tests (1-27, 29, plus the three supplementary 2D CFD configurations), each .npz file contains:
preds: model predictions, shape [N_test, spatial_dims..., T, nc]
targets: ground truth, same shape
per_sample: per-sample… See the full description on the dataset page: https://huggingface.co/datasets/pdebench-fno-audit/fno-predictions.dolly-audio-1000h-vietnamese
Dolly-Audio: Vietnamese Multi-Speaker High-Quality Speech Corpus
Dataset Summary
Dolly-Audio is a large-scale, high-quality Vietnamese speech corpus created by the Dolly AI Team.
Inspired by Dolly, the world’s first cloned mammal, the project aims to advance research in Vietnamese speech synthesis, speech recognition, and voice modeling.
This release provides nearly 1,000 hours of professionally cleaned audio, featuring 152 speakers across different Vietnamese regions and… See the full description on the dataset page: https://huggingface.co/datasets/fnooub/dolly-audio-1000h-vietnamese.dataset-rbc-fno
Rayleigh-Benard Convection (RBC) Dataset
This dataset contains Direct Numerical Simulation (DNS) data of Rayleigh-Benard convection in two and three dimensions, generated using Oceananigans.jl. It accompanies the paper Fourier neural operators as data-driven surrogates for two- and three-dimensional Rayleigh-Benard convection, published in Neurocomputing (2026).
Dataset Description
Rayleigh-Benard Convection describes convection in a fluid layer heated from below and… See the full description on the dataset page: https://huggingface.co/datasets/tmarkmann/dataset-rbc-fno.DA-FNOThis model was trained using the following environment:
Python 3.9
PyTorch 2.2.2
numpy 1.24
CUDA 12.6
comparison: Comparison of the DA-FNO with different theta and Conv-FNO and vanilla FNO models.
final_model: DA-FNO model trained on the entire training set.
dataset: The first 200 samples in the training set.
spectrum_2700: Average spectrum of the training set.
navier-stokes-2d-fno
Navier-Stokes 2D (ν = 1e-3)
Simulations of the 2D Navier-Stokes equation for a viscous, incompressible fluid in
vorticity form on the unit torus, following the Fourier Neural Operator (FNO) benchmark
of Li et al. (2021).
Each sample is the time evolution of the vorticity field w(x, y, t) on a periodic
64 × 64 grid over 20 time steps.
Intended use: this dataset is meant to be used for both training and testing /
evaluation of neural operators and PDE surrogate models. It is… See the full description on the dataset page: https://huggingface.co/datasets/abelsr1710/navier-stokes-2d-fno.muTransfer-FNO-data
muTransfer-FNO Dataset
Benchmark datasets for Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators (ICML 2025).
Code: https://github.com/LithiumDA/muTransfer-FNO
Contains data for three PDE problems: Navier-Stokes, Burgers' equation, and Darcy Flow.
File Structure
├── ns/
│ ├── get_full_data.py # Script to combine NS parts
│ ├── ns_part_01.npy # Navier-Stokes samples 0–99
│ ├── ns_part_02.npy… See the full description on the dataset page: https://huggingface.co/datasets/LDA1020/muTransfer-FNO-data.fno-vorticityNavier-Stokes datasets with ν=1e-4 and ν=1e-5 from the Fourier Neural Operator paper in numpy format.
fno-3D-source-unmixing
3D FNO Source Unmixing Dataset
Its a dataset of 3D signals designed for seperating complex non linearly mixed fields using fnos.
Dataset Summary
File Name: fno_3D_source.pt
Total Samples: 20,000
Tensor Shape: (20000, 2, 16, 16, 16)
Data Type: torch.float32
Uncompressed Size: ~625 MB
Boundary Condition: I've applied a 3D Hann window envelope so the signal smoothly decays to zero at the spatial boundaries.
Signal Generation & Physics
The observed… See the full description on the dataset page: https://huggingface.co/datasets/rohithp-alt2/fno-3D-source-unmixing.FNOBenchmarkData used to benchmark Fourier Neural Operator (FNO) using CARAML.
Rayleigh-Bénard convection (RBC)
RBC2D data is generated using Dedalus solver and RBC3D data is generated using pySDC solver.
dataset: RBC2D_256x64_Ra1e7_dt1e-3_update.h5
-- grid shape : (256, 64)
-- grid domain : [0.0, 4.0] x [0.0, 1.0]
-- nSimu : 10
-- dtData : 0.001
-- inSize : 1
-- outStep : 1
-- inStep : 500
-- nSamples (per simu) : 200
-- nSamples (total) : 2000
-- dtInput : 0.001
-- outType :… See the full description on the dataset page: https://huggingface.co/datasets/chelseajohn/FNOBenchmark.navier-stokes-2d-fno
Navier-Stokes 2D (ν = 1e-3)
Simulations of the 2D Navier-Stokes equation for a viscous, incompressible fluid in
vorticity form on the unit torus, following the Fourier Neural Operator (FNO) benchmark
of Li et al. (2021).
Each sample is the time evolution of the vorticity field w(x, y, t) on a periodic
64 × 64 grid over 20 time steps.
Intended use: this dataset is meant to be used for both training and testing /
evaluation of neural operators and PDE surrogate models. It is… See the full description on the dataset page: https://huggingface.co/datasets/viper333qaq/navier-stokes-2d-fno.fno-flowers
Dataset Card for "fno-flowers"
More Information needed
FNO-RBC2D_paper_artefacts
FNO Paper Data
The folder contains the data and model artifacts used in training and evaluating the FNO models:
dedalus_data : Simulation data generated with Dedalus, used for FNO model training and evaluation.
FNO_model_lookup.xlsx : Excel spreadsheet detailing the architecture and configuration of each FNO model.
loss_data: Training loss logs stored as text files, indexed by the run_index from FNO_model_lookup.xlsx.
model_checkpoint : PyTorch model checkpoints, also indexed by… See the full description on the dataset page: https://huggingface.co/datasets/chelseajohn/FNO-RBC2D_paper_artefacts.fno-full-flowers
Dataset Card for "fno-full-flowers"
More Information needed
fno-cifar10-32
Dataset Card for "fno-cifar10-32"
More Information needed
fno-datadual-fno-cifar10-32
Dataset Card for "dual-fno-cifar10-32"
More Information needed
ax650-fnOS-data-package
AX650 fnOS Data Package
This repository contains offline demo media and an Immich deployment bundle for an AX650 device running fnOS.
Contents
Path
Description
image/fnos_AX650N_Demo_V1.1.31_AXSDK_V3.16.0_20260810-144946.axp
fnOS/AX650 demo application package.
immich/immich-axera-aarch64-v3.0.1.zip
Offline Immich package for 64-bit ARM (AArch64), including Compose files and Docker image archives.
immich/deploy-immich.sh
Interactive deployment… See the full description on the dataset page: https://huggingface.co/datasets/yxran001/ax650-fnOS-data-package.dual-fno-lsun-256fno-lsun-256fNOAhDV0CAIpAmMXfno383r7g8isbko3