# ssraghuvanshi/panet architecture

> Architecture diagram of the GitHub repository ssraghuvanshi/panet, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-07-04). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ssraghuvanshi/panet
- Repository: https://github.com/ssraghuvanshi/panet

## Overview

##### Project Type and Purpose
- This is a deep‐learning research codebase for 3D medical image segmentation (BraTS 2020) using a Prior Attention Network (PANet).
- It includes training (train.py), inference (inference.py), model definitions (models/), configuration files (configs/), and data utilities (utils/).

##### File Structure Analysis
Top-level:
- configs/ — optimizer configuration files (adam.cfg, sgd.cfg)
- train.py — main training entry point
- inference.py — main inference entry point
- models/ — all network architectures and building blocks
- utils/ — data loading, augmentation, iterator logic
Patterns:
- Modular separation of concerns: configurations, data pipeline, model definitions, scripts
- Plug-and-play optimizers via configs
- Clear training vs. inference scripts

##### Key Components
a. Data Ingestion & Preprocessing
– External Data Store (./data) containing raw MRI volumes
– utils/data_pipeline.py: patch extraction, normalization, augmentation
– utils/iterator.py: batching and sampling (training vs. validation)
b. Configuration Management
– configs/*.cfg loaded at startup by train.py and inference.py to set hyperparameters, optimizer type, scheduler, mixed precision flags
c. Model Stack
– models/basic_modules.py: core convolutional layers, normalization, activation modules
– models/attention_blocks.py: prior attention mechanisms, parameterized skip connections
– models/networks.py: end‐to‐end PANet architecture, deep supervision heads
d. Training Loop (train.py)
– Reads configs → initializes data iterator → builds model → sets optimizer/scheduler → runs epochs with patch-based data feeding
– Implements deep supervision losses and intermediate attention guidance
– Checkpointing (model + optimizer + scheduler states)
e. Inference Pipeline (inference.py)
– Loads checkpoint → uses same patch-based pipeline → stitches 3D patches to full volume → outputs segmentation maps

##### Relationships & Data Flow
1. External Data → Data Pipeline → Iterator → Model Forward Pass
2. Model Outputs + Ground Truth → Loss Computation (deep supervision) → Backprop → Optimizer Update
3. Model Checkpoint → Saved to disk → Re‐loaded by inference.py
4. Inference: Iterator → Model → Post-processing → Segmentation Output

##### Architectural Patterns and Principles
- Modular separation: scripts (train/inference), configs, utils, models
- Pipeline pattern for data flow (chain of responsibility)
- Plug-in configuration (config files determine optimizer, mixed precision, data handling)
- Layered model definition (basic modules → attention blocks → full network)

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% CLI Layer
    subgraph "CLI Layer"
        Train["train.py"]:::script
        Inference["inference.py"]:::script
    end

    %% Configuration Layer
    subgraph "Configuration Layer"
        CFG_ADAM["adam.cfg"]:::config
        CFG_SGD["sgd.cfg"]:::config
    end

    %% Data Layer
    subgraph "Data Layer"
        DataStore["Data Store\n(./data)"]:::data
        DP["data_pipeline.py"]:::data
        IT["iterator.py"]:::data
    end

    %% Model Layer
    subgraph "Model Layer"
        Basic["basic_modules.py"]:::model
        Attn["attention_blocks.py"]:::model
        Net["networks.py"]:::model
    end

    %% Training Components
    subgraph "Training Components"
        Loss["Loss & Metrics"]:::train
        Opt["Optimizer & Scheduler"]:::train
        CKPT["Checkpoint Manager"]:::train
    end

    %% Inference Components
    subgraph "Inference Components"
        CKPTL["Checkpoint Loader"]:::infer
        Post["Post-processing & Output Writer"]:::infer
    end

    %% External Infrastructure
    GPU["GPU (CUDA)"]:::infra
    Log["Logging System"]:::infra

    %% Relationships
    Train -->|load configs| CFG_ADAM
    Train -->|load configs| CFG_SGD
    Inference -.->|load configs| CFG_ADAM
    Inference -.->|load configs| CFG_SGD

    Train -->|read data| DataStore
    Inference -->|read data| DataStore

    DataStore -->|patch extraction| DP
    DP -->|batching/sampling| IT

    IT -->|forward pass| Basic
    Basic --> Attn
    Attn --> Net

    Net -->|compute loss| Loss
    Loss -->|backprop| Opt
    Opt -->|save state| CKPT
    CKPT -.->|load checkpoint| CKPTL

    CKPTL -->|forward pass| Net
    Net -->|stitch patches| Post

    Train -->|logging| Log
    Inference -->|logging| Log
    Train -->|compute on| GPU
    Inference -->|compute on| GPU

    %% Click Events
    click DP "https://github.com/ssraghuvanshi/panet/blob/main/utils/data_pipeline.py"
    click IT "https://github.com/ssraghuvanshi/panet/blob/main/utils/iterator.py"
    click CFG_ADAM "https://github.com/ssraghuvanshi/panet/blob/main/configs/adam.cfg"
    click CFG_SGD "https://github.com/ssraghuvanshi/panet/blob/main/configs/sgd.cfg"
    click Basic "https://github.com/ssraghuvanshi/panet/blob/main/models/basic_modules.py"
    click Attn "https://github.com/ssraghuvanshi/panet/blob/main/models/attention_blocks.py"
    click Net "https://github.com/ssraghuvanshi/panet/blob/main/models/networks.py"
    click Train "https://github.com/ssraghuvanshi/panet/blob/main/train.py"
    click Inference "https://github.com/ssraghuvanshi/panet/blob/main/inference.py"

    %% Styles
    classDef script fill:#F5A623,stroke:#E67E22,color:#000
    classDef config fill:#3498DB,stroke:#2980B9,color:#fff
    classDef data fill:#85C1E9,stroke:#5DADE2,color:#000
    classDef model fill:#82E0AA,stroke:#27AE60,color:#000
    classDef train fill:#F9E79F,stroke:#F1C40F,color:#000
    classDef infer fill:#F5B7B1,stroke:#EC7063,color:#000
    classDef infra fill:#D5D8DC,stroke:#A6ACAF,color:#000
```
