polymathic-ai / UNetClassic-MHD_64

huggingface.co
Total runs: 4
24-hour runs: 0
7-day runs: 2
30-day runs: 3
Model's Last Updated: March 28 2025

Introduction of UNetClassic-MHD_64

Model Details of UNetClassic-MHD_64

Benchmarking Models on the Well

The Well is a 15TB dataset collection of physics simulations. This model is part of the models that have been benchmarked on the Well.

The models have been trained for a fixed time of 12 hours or up to 500 epochs, whichever happens first. The training was performed on a NVIDIA H100 96GB GPU. In the time dimension, the context length was set to 4. The batch size was set to maximize the memory usage. We experiment with 5 different learning rates for each model on each dataset. We use the model performing best on the validation set to report test set results.

The reported results are here to provide a simple baseline. They should not be considered as state-of-the-art . We hope that the community will build upon these results to develop better architectures for PDE surrogate modeling.

U-Net

Implementation of the U-Net model .

Model Details

For benchmarking on the Well, we used the following parameters.

Parameters Values
Spatial Filter Size 3
Initial Dimension 48
Block per Stage 1
Up/Down Blocks 4
Bottleneck Blocks 1
Trained Model Versions

Below is the list of checkpoints available for the training of U-Net on different datasets of the Well.

Dataset Learning Rate Epochs VRMSE
acoustic_scattering (maze) 1E-2 26 0.0395
active_matter 5E-3 239 0.2609
convective_envelope_rsg 5E-4 19 0.0701
gray_scott_reaction_diffusion 1E-2 44 0.5870
helmholtz_staircase 1E-3 120 0.01655
MHD_64 5E-4 165 0.1988
planetswe 1E-2 49 0.3498
post_neutron_star_merger - -
rayleigh_benard 1E-4 29 0.8448
rayleigh_taylor_instability 5E-4 193 0.6140
shear_flow 5E-4 29 0.836
supernova_explosion_64 5E-4 46 0.3242
turbulence_gravity_cooling 1E-3 14 0.3152
turbulent_radiative_layer_2D 5E-3 500 0.2394
viscoelastic_instability 5E-4 198 0.3147
Loading the model from Hugging Face

To load the UNetClassic model trained on the MHD_64 of the Well, use the following commands.

from the_well.benchmark.models import UNetClassic

model = UNetClassic.from_pretrained("polymathic-ai/UNetClassic-MHD_64")

Runs of polymathic-ai UNetClassic-MHD_64 on huggingface.co

4
Total runs
0
24-hour runs
0
3-day runs
2
7-day runs
3
30-day runs

More Information About UNetClassic-MHD_64 huggingface.co Model

UNetClassic-MHD_64 huggingface.co

UNetClassic-MHD_64 huggingface.co is an AI model on huggingface.co that provides UNetClassic-MHD_64's model effect (), which can be used instantly with this polymathic-ai UNetClassic-MHD_64 model. huggingface.co supports a free trial of the UNetClassic-MHD_64 model, and also provides paid use of the UNetClassic-MHD_64. Support call UNetClassic-MHD_64 model through api, including Node.js, Python, http.

polymathic-ai UNetClassic-MHD_64 online free

UNetClassic-MHD_64 huggingface.co is an online trial and call api platform, which integrates UNetClassic-MHD_64's modeling effects, including api services, and provides a free online trial of UNetClassic-MHD_64, you can try UNetClassic-MHD_64 online for free by clicking the link below.

polymathic-ai UNetClassic-MHD_64 online free url in huggingface.co:

https://huggingface.co/polymathic-ai/UNetClassic-MHD_64

UNetClassic-MHD_64 install

UNetClassic-MHD_64 is an open source model from GitHub that offers a free installation service, and any user can find UNetClassic-MHD_64 on GitHub to install. At the same time, huggingface.co provides the effect of UNetClassic-MHD_64 install, users can directly use UNetClassic-MHD_64 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

UNetClassic-MHD_64 install url in huggingface.co:

https://huggingface.co/polymathic-ai/UNetClassic-MHD_64

Url of UNetClassic-MHD_64

UNetClassic-MHD_64 huggingface.co Url

Provider of UNetClassic-MHD_64 huggingface.co

polymathic-ai
ORGANIZATIONS

Other API from polymathic-ai