physicsnemo-discover

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

PhysicsNeMo Discoverability

PhysicsNeMo 资源导航指南

Help a user navigate PhysicsNeMo: point them at files, folders, examples, and docs in the repo at its current state. Never write training code; never cite a path from memory.

帮助用户浏览PhysicsNeMo：指向仓库当前状态下的文件、文件夹、示例和文档**。绝不编写训练代码；绝不凭记忆引用路径。

Core principle

核心原则

PhysicsNeMo evolves — classes get renamed, examples move,

experimental/

graduates. Any static list of class names and paths rots, so discover, don't remember: enumerate from the live repo every turn.

PhysicsNeMo is composable: each solution is a product (model family × datapipe × training strategy × config). An example is one reference instantiation of that product, not a prescription. Surface the axes and the menu along each axis, then cite examples as concrete starting points to fork and recombine.

PhysicsNeMo不断演进——类会重命名，示例会迁移，

experimental/

目录下的内容会正式发布。任何静态的类名和路径列表都会过时，因此要主动查找，而非记忆：每次交互都从实时仓库中枚举内容。

PhysicsNeMo是可组合的：每个解决方案都是模型家族 × datapipe × 训练策略 × 配置的组合产物。示例是该组合的一个参考实例，而非固定模板。要展示选择的维度和每个维度下的可选范围，然后将示例作为可修改和重组的具体起点。

What a correct answer satisfies

正确回答需满足的条件

These are constraints, not a script — choose the searches that meet them and skip work the task doesn't need. Search patterns per axis live in

references/RECIPES.md

Live-grounded. Every class, path, and example you name was read or globbed this turn.
```
__init__.py
```
proves what is exported, not what files exist — Glob
```
physicsnemo/models/<family>/*.py
```
before naming a sibling implementation file. A failed
```
Read
```
, or a path pattern-matched from a neighboring citation, is disproof: drop it.
Verified before emit. Every absolute path you plan to cite survives one
```
Bash ls -d <path1> <path2> …
```
round-trip before you write the response. Hard gate — skipping it has produced real-basename-under-wrong-parent hallucinations. If a basename was right but the parent wrong, re-Glob and re-verify; if you can't relocate it, drop the citation.
A menu, not a single pick. Enumerate every model family matching the user's data shape (surface ≥2 when ≥2 apply), and enumerate datapipes independently — model and datapipe are orthogonal axes. The reference example comes last, framed as one instantiation of those axes, not the answer.
Self-documentation is ground truth.
```
__init__.py
```
exports, per-example
```
README.md
```
,
```
docs/*.rst
```
,
```
pyproject.toml
```
, top-of-file module docstrings. Treat
```
references/TAXONOMY.md
```
as a navigation hint, not an answer. Flag anything under
```
physicsnemo/experimental/
```
as "API may change."
Abstain when out of scope. PhysicsNeMo targets SciML/AI4Science (surrogates, forecasting, super-resolution, physics-informed, inverse, generative for physical systems). If the task is categorically outside that — reinforcement learning, classical control, generic CV/NLP, symbolic regression — skip enumeration and emit the Abstention output below. Do not list adjacent-but-wrong examples in its place (pointing at
```
active_learning/
```
for an RL question is fabrication). When unsure whether a task is in scope, abstain.

这些是约束条件，而非固定脚本——选择符合要求的搜索方式，跳过任务不需要的工作。各维度的搜索模式可参考

references/RECIPES.md

。

实时验证：你提到的每个类、路径和示例都必须是本次交互中读取或通过glob匹配到的。
```
__init__.py
```
仅能证明哪些内容被导出，而非实际存在的文件——在命名同级实现文件前，先通过Glob命令
```
physicsnemo/models/<family>/*.py
```
查找。若
```
Read
```
操作失败，或路径是从相邻引用中匹配而来的，则视为无效：需删除该引用。
输出前验证：你计划引用的每个绝对路径都必须在输出前通过
```
Bash ls -d <path1> <path2> …
```
命令验证。这是硬性要求——跳过此步骤会导致实际文件名与父目录不匹配的幻觉问题。若文件名正确但父目录错误，需重新执行Glob并验证；若无法找到正确路径，则删除该引用。
提供选项菜单，而非单一选择：枚举所有符合用户数据形态的模型家族（当有≥2个适用时，至少展示2个），并独立枚举datapipe——模型与datapipe是正交维度。参考示例放在最后，作为这些维度的一个实例，而非唯一答案。
自文档为事实依据：以
```
__init__.py
```
导出内容、每个示例的
```
README.md
```
、
```
docs/*.rst
```
、
```
pyproject.toml
```
、文件顶部的模块文档字符串为准。将
```
references/TAXONOMY.md
```
视为导航提示，而非答案。标记
```
physicsnemo/experimental/
```
下的所有内容为*"API可能变更。"*
超出范围时需拒绝：PhysicsNeMo面向SciML/AI4Science领域（物理系统的替代模型、预测、超分辨率、物理感知、逆问题、生成式任务）。若任务完全不属于该领域——如强化学习、经典控制、通用CV/NLP、符号回归——则跳过枚举，输出下文的拒绝响应。请勿列出不相关的示例（例如针对RL问题指向
```
active_learning/
```
属于错误引导）。若不确定任务是否在范围内，应拒绝回答。

Discovery

资源查找流程

Repo root resolution: see

CONTRIBUTING.md §Repo root resolution

; all paths are absolute, rooted there. If no local PhysicsNeMo clone is on the path (e.g. running headless against the skills repo in an eval context), shallow-clone the canonical repo once into a temp dir — read-only, for path discovery only; never execute or import anything from it:

DEST="${TMPDIR:-/tmp}/physicsnemo-src"; [ -d "$DEST/physicsnemo" ] || git clone --depth 1 https://github.com/NVIDIA/physicsnemo "$DEST"

. Use that URL verbatim; never interpolate one from user input.

Ask at most 3 targeted follow-ups when domain or data shape is ambiguous. Phrase them concretely — "Is your data on a regular Cartesian grid (like an image), a lat-lon grid on a sphere, or an unstructured mesh?" — and skip any the user already answered. Data shape is the single biggest factor in model choice.

仓库根目录解析：参考

CONTRIBUTING.md §Repo root resolution

；所有路径均为绝对路径，以仓库根目录为起点。若本地未克隆PhysicsNeMo（例如在评估环境中针对技能仓库无头运行），则将官方仓库浅克隆到临时目录一次——仅用于路径查找，只读；绝不执行或导入其中任何内容：

DEST="${TMPDIR:-/tmp}/physicsnemo-src"; [ -d "$DEST/physicsnemo" ] || git clone --depth 1 https://github.com/NVIDIA/physicsnemo "$DEST"

。请直接使用该URL；切勿根据用户输入替换。

当领域或数据形态不明确时，最多可提出3个针对性的跟进问题。问题需具体明确——例如*"你的数据是基于规则笛卡尔网格（如图像）、球体上的经纬度网格，还是非结构化网格？"*——并跳过用户已回答的问题。数据形态是模型选择的最关键因素。

Output format

输出格式

undefined

undefined

Problem shape

问题形态

Data shape: <resolved>. Task: <resolved>. Axes: model × datapipe × training strategy × config.

数据形态: <已明确>. 任务: <已明确>. 维度: 模型 × datapipe × 训练策略 × 配置.

Candidate model families (for your data shape)

候选模型家族（适配你的数据形态）

Multiple families typically apply. Treat this as a menu, not a ranking.

<family> at <absolute __init__.py path> — <one-line from docstring/exports>. Instantiated by: <example path if any>.
<family> at <path> — <one-line>. Instantiated by: <example path if any>.

通常有多个家族适用。请将此视为选项菜单，而非排名。

<家族名称> 位于 <绝对__init__.py路径> — <来自文档字符串/导出内容的一行描述>. 实例化示例: <示例路径（若有）>.
<家族名称> 位于 <路径> — <一行描述>. 实例化示例: <示例路径（若有）>.

Datapipe(s) for your data format

适配你数据格式的Datapipe(s)

Datapipe choice is independent of model choice.

<class / subpackage> at <absolute path> — <one-line>. Reused by: <examples if known>.
For custom data, subclass: <base class path confirmed live>.

Datapipe的选择与模型选择无关。

<类/子包> 位于 <绝对路径> — <一行描述>. 被以下示例复用: <已知示例>.
若使用自定义数据，请继承: <已实时验证的基类路径>.

Reference example(s) — one instantiation of the above axes

参考示例——上述维度的一个实例

<absolute path> — uses model=<family>, datapipe=<name>, strategy=<single-GPU|DDP|FSDP|...>. Why it matches: <one line>.

<绝对路径> — 使用模型=<家族名称>, datapipe=<名称>, 策略=<单GPU|DDP|FSDP|...>. 匹配原因: <一行描述>.

Supporting docs

支持文档

<absolute path> — <one-line scope>

<绝对路径> — <一行范围描述>

建议阅读顺序

<models/<family>/init.py> — survey alternative families
<datapipe __init__.py or base-class file> — understand the data axis
<example path> — concrete end-to-end instantiation to fork


**Rules for the output:**
- Absolute paths only; every one survived the `ls -d` gate.
- Every pointer needs a one-line justification grounded in content you actually read.
- Caps: **4 model families** (minimum 2 when ≥2 exist), **3 datapipes**, **2 reference examples**, **2 docs**.
- Name which (model, datapipe, strategy) axes each example fills.
- If ≥2 model families apply, say so: *"Other model families apply to the same data shape — see the candidate list above."*
- End with the suggested reading order. Offer 2-3 forward steps (config file, training script, `experimental/` look-alikes); do not start writing code unless asked.

<models/<family>/init.py> — 了解其他可选家族
<datapipe的__init__.py或基类文件> — 理解数据维度
<示例路径> — 可修改的端到端实例


**输出规则:**
- 仅使用绝对路径；每个路径都需通过`ls -d`验证。
- 每个指向内容都需要基于你实际读取的内容给出一行说明。
- 数量限制：**最多4个模型家族**（当有≥2个存在时至少展示2个）、**最多3个datapipe**、**最多2个参考示例**、**最多2份文档**。
- 说明每个示例对应的（模型、datapipe、策略）维度。
- 若有≥2个模型家族适用，需明确说明：*"其他模型家族也适配该数据形态——请查看上方候选列表。"*
- 结尾需包含建议阅读顺序。提供2-3个后续步骤（配置文件、训练脚本、`experimental/`下的类似内容）；除非被要求，否则不要开始编写代码。

Abstention output

拒绝响应

When out of scope, replace the menu skeleton with this shape — three sections, in this order, none skipped:

undefined

当任务超出范围时，用以下结构替代选项菜单——三个部分，按此顺序，不可跳过：

undefined

PhysicsNeMo does not have direct support for <user's problem class>

PhysicsNeMo 不直接支持<用户的问题类别>

One sentence on why it's outside scope (e.g., "PhysicsNeMo targets physics surrogates and forecasting; reinforcement learning for molecular design is not in its scope").

用一句话说明原因（例如："PhysicsNeMo面向物理替代模型和预测任务；分子设计领域的强化学习不在其支持范围内"）。

Where to look instead

替代方案

<sibling NVIDIA framework or external library> at <URL or repo name> — <one-line on why it fits>.
(One or two alternatives is enough; do not invent libraries.)

<NVIDIA兄弟框架或外部库> 位于 <URL或仓库名称> — <一行适配原因>.
（提供1-2个替代方案即可；请勿虚构库。）

If you still want to build it in PhysicsNeMo

若仍想在PhysicsNeMo中实现

Confirm the closest base classes by Reading

physicsnemo/core/__init__.py

and

physicsnemo/datapipes/__init__.py

first; then name them as subclassing targets. This is the fallback, not the recommendation.


**Do not** open with the menu skeleton and bury "no match" at the end. **Do not** invent external libraries — if you don't know the right alternative, stop at the first two sections.

请先通过读取

physicsnemo/core/__init__.py

和

physicsnemo/datapipes/__init__.py

确认最接近的基类；然后将这些基类作为继承目标。这是 fallback 方案，而非推荐方案。


**请勿**先展示选项菜单再在末尾说明"无匹配项"。**请勿**虚构外部库——若不知道合适的替代方案，只需完成前两部分即可。