# pym1024/swap architecture

> Architecture diagram of the GitHub repository pym1024/swap, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/pym1024/swap
- Repository: https://github.com/pym1024/swap

## Overview

##### Project type and purpose
- This is a research tool/library for computing the SWAP‐Score—a zero‐cost proxy metric that predicts neural network performance without full training.
- It provides:
- A command‐line entrypoint (`correlation.py`) to compute correlations between SWAP‐Score and actual CIFAR-10 accuracies.
- Core metric implementation under `src/metrics/swap.py`.
- Utilities for data loading, search‐space definition, and generic helper functions.

##### File structure
- Top‐level:
- `correlation.py` – script to read a precomputed CSV of architectures+accuracies, compute SWAP scores, and output correlations.
- `datasets/` – contains the CSV file `DARTS_archs_CIFAR10.csv` for 1,000 architectures and results.
- `requirements.txt` – Python dependencies.
- `src/` package decomposition:
- `src/datasets/` – modules to load CIFAR-10 or Downsampled ImageNet data (`DownsampledImageNet.py`, generic utils).
- `src/search_space/` – definitions of architectural primitives (`operations.py`, `networks.py`).
- `src/metrics/` – core SWAP‐Score logic (`swap.py`).
- `src/utils/` – shared helper functions.

##### README for architectural hints
- Emphasizes that `src/metrics/swap.py` contains the core algorithm.
- The pipeline: install dependencies → run `python correlation.py` → measure correlation between SWAP and true accuracies.

a. Main components
- Entrypoint: correlation.py
- Data sources:
- `datasets/DARTS_archs_CIFAR10.csv`
- (Optional) Downsampled ImageNet loader in `src/datasets`
- Search‐space module (`src/search_space`)
- SWAP‐Score metric module (`src/metrics/swap.py`)
- Utility functions (`src/utils`)
- Output: correlation results (console/table/graph)
b. Component interactions
1. correlation.py reads CSV → hands off architecture definitions and true accuracies.
2. correlation.py invokes search_space to reconstruct each model’s graph and parameters.
3. correlation.py calls the SWAP module, passing models + sample data loaders → computes SWAP‐Scores.
4. correlation.py computes statistical correlation between SWAP‐Scores and true accuracies.
5. Results are printed or saved.
c. Architectural patterns
- Modular package structure separating concerns: data ingestion, search‐space abstraction, metric computation, and orchestration.
- Pipeline pattern: linear data flow from entrypoint → loader → model definition → metric computation → analysis.
d. Key technologies
- Python 3.x
- pandas / numpy (for CSV and data manipulation)
- PyTorch or NumPy (within `swap.py` for activation hooks and pattern extraction)
- Virtual environment via `requirements.txt`

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Orchestration
    Script["correlation.py: Entrypoint"]:::orchestration

    %% Data Modules
    CSV["datasets/DARTS_archs_CIFAR10.csv"]:::data
    subgraph "src/datasets"
        Loader["DownsampledImageNet.py: Data Loader"]:::data
        DataUtils["utilities.py: Dataset Utils"]:::data
    end

    %% Search Space
    subgraph "src/search_space"
        Operations["operations.py: Primitive Operations"]:::data
        Networks["networks.py: Network Definitions"]:::data
    end

    %% Metrics
    Swap["swap.py: SWAP-Score Computation"]:::metrics

    %% Utilities
    Util["utilities.py: Shared Helpers"]:::util

    %% Artifacts
    Requirements["requirements.txt"]:::docs
    README["README.md"]:::docs
    LICENSE["LICENSE.md"]:::docs

    %% Data flows
    CSV -->|loads architectures & accuracies| Script
    Loader -->|optional data load| Script
    DataUtils -->|preprocessing helpers| Script

    %% Search-space integration
    Operations -->|define primitives| Script
    Networks -->|define architectures| Script

    %% Metric computation
    Script -->|invoke| Swap
    Swap -->|return swap_scores| Script

    %% Utilities usage
    Util -->|shared functions| Script
    Util -->|shared functions| Swap

    %% Dependencies and docs
    Requirements -->|env setup| Script
    README -.-> Script
    LICENSE -.-> Script

    %% Click Events
    click Script "https://github.com/pym1024/swap/blob/main/correlation.py"
    click CSV "https://github.com/pym1024/swap/blob/main/datasets/DARTS_archs_CIFAR10.csv"
    click Loader "https://github.com/pym1024/swap/blob/main/src/datasets/DownsampledImageNet.py"
    click DataUtils "https://github.com/pym1024/swap/blob/main/src/datasets/utilities.py"
    click Operations "https://github.com/pym1024/swap/blob/main/src/search_space/operations.py"
    click Networks "https://github.com/pym1024/swap/blob/main/src/search_space/networks.py"
    click Swap "https://github.com/pym1024/swap/blob/main/src/metrics/swap.py"
    click Util "https://github.com/pym1024/swap/blob/main/src/utils/utilities.py"
    click Requirements "https://github.com/pym1024/swap/blob/main/requirements.txt"
    click README "https://github.com/pym1024/swap/blob/main/README.md"
    click LICENSE "https://github.com/pym1024/swap/blob/main/LICENSE.md"

    %% Styles
    classDef data fill:#ADD8E6,stroke:#000,stroke-width:1px
    classDef metrics fill:#90EE90,stroke:#000,stroke-width:1px
    classDef orchestration fill:#FFD700,stroke:#000,stroke-width:1px
    classDef util fill:#D3D3D3,stroke:#000,stroke-width:1px
    classDef docs fill:#F0E68C,stroke:#000,stroke-width:1px
```
