---
title: INFINITY
canonical_url: "https://www.modelscope.cn/models/wangqi0928/INFINITY"
md_url: "https://www.modelscope.cn/models/wangqi0928/INFINITY.md"
repository: wangqi0928/INFINITY
chinese_name: INFINITY
last_updated: 2026-07-17
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 0
stars: 0
---

# INFINITY

> INFINITY - wangqi0928 在 ModelScope 开源的模型。对论文 INFINITY: Neural Field Modeling for Reynolds-Averaged Navier-Stokes Equations（arXiv:2307.13538）中模型在 AirfRANS 数据集上的复现实现。代码实现完全基于论文正文（Figure 1、Algorithm 1、Table 1）及公开数据构建，未参考任何官方或第三方实现。

- **Repository**: wangqi0928/INFINITY
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-07-17

Source: https://www.modelscope.cn/models/wangqi0928/INFINITY

---

# INFINITY on AirfRANS

Reproduction of **INFINITY: Neural Field Modeling for Reynolds-Averaged Navier-Stokes Equations**
(arXiv:2307.13538) on the AirfRANS dataset. Implementation is derived solely from the paper
text (Figure 1, Algorithm 1, Table 1) and the provided data.

## Model

- 6 modulated INRs (Fourier Features + FiLM shift): `d, n, vx, vy, p, nut`
- Hypernetworks mapping latent code `z_u` -> modulation `phi_u`
- Mapping network `g_psi` (MLP): `(z_d, z_n, Vx, Vy)` -> `(z_vx, z_vy, z_p, z_nut)`
- Two-stage training: (1) CAVIA second-order meta-learning of INRs (Algorithm 1, K=3 inner steps),
  (2) supervised MSE in z-code space for `g_psi`.

## Structure

- `config/` - Configuration YAML and manifest JSON files
- `model/` - Model architecture definitions (INFINITY, ModulatedINR, FourierFeatures, Hypernetwork)
- `scripts/` - Training, evaluation, data loading, and utility scripts
- `weight/` - Pre-trained model checkpoint files for various configurations

## Run

```bash
python scripts/train.py config/infinity.yaml        # stage 1 + stage 2
python scripts/evaluate.py config/infinity.yaml     # Table-1 style metrics
```

## Config

All hyperparameters in `config/infinity.yaml` (paper only fixes K=3; others are default assumptions).

## Configurations

| Config | Description |
|---|---|
| `config/tiny.yaml` | Tiny model for smoke testing |
| `config/small.yaml` | Small model |
| `config/medium.yaml` | Medium model |
| `config/large.yaml` | Large scale |
| `config/large_bias.yaml` | Large with surface bias sampling |
| `config/large_n4096.yaml` | Large with 4096 points |
| `config/infinity.yaml` | Default INFINITY config |