# anjanisu/dfutissuesegnet architecture

> Architecture diagram of the GitHub repository anjanisu/dfutissuesegnet, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-08). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/anjanisu/dfutissuesegnet
- Repository: https://github.com/anjanisu/dfutissuesegnet

## Overview

This repository trains four-class DFU tissue segmentation models using labeled images and progressively pseudo-labeled unlabeled images. The intended workflow is supervised training, Phase 1 pseudo-labeling and semi-supervised refinement, then Phase 2 pseudo-labeling and refinement; evaluation and loss-curve generation provide comparison and diagnostics. The README documents the model architecture and full workflow. Source excerpts show training, inference, and evaluation behavior, but the master script references a `Codes/` directory absent from the tree, so its runnable orchestration is uncertain.

Main entry points: [`codx/semisupervised_training_phase1_local.py`](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/semisupervised_training_phase1_local.py) (Phase 1 semi-supervised), [`codx/run_master_pipeline.py`](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/run_master_pipeline.py) (Pipeline launcher), [`codx/semisupervised_training_phase2_local.py`](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/semisupervised_training_phase2_local.py) (Phase 2 semi-supervised), [`codx/pseudo_label_generation_phase2_local.py`](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/pseudo_label_generation_phase2_local.py) (Phase 2 pseudo-labels)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_training["Model training"]
  node_supervised["Supervised training"]
  node_architecture["Segmentation model"]
  node_semi1["Phase 1 semi-supervised"]
  node_semi2["Phase 2 semi-supervised"]
  node_master["Pipeline launcher"]
end

subgraph group_labeling["Pseudo-labeling"]
  node_pseudo1["Phase 1 pseudo-labels"]
  node_pseudo2["Phase 2 pseudo-labels"]
end

subgraph group_artifacts["Models and results"]
  node_checkpoints[("Model checkpoints")]
  node_pseudo_store[("Pseudo-label files")]
  node_metrics[("Training metrics")]
  node_log["Phase results log<br/>[output.txt]"]
end

subgraph group_analysis["Evaluation and diagnostics"]
  node_evaluation["Phase evaluation"]
  node_curves["Combined loss curves"]
  node_single_curves["Per-run loss curves"]
  node_metric_search["Metric search"]
end

node_researcher(("Researcher"))
node_dataset[("DFUTissue data")]

node_researcher -->|"starts"| node_master
node_dataset -->|"labeled images"| node_supervised
node_supervised -->|"trains"| node_architecture
node_supervised -->|"saves checkpoint"| node_checkpoints
node_supervised -->|"writes metrics"| node_metrics
node_checkpoints -->|"loads model"| node_pseudo1
node_dataset -->|"unlabeled images"| node_pseudo1
node_pseudo1 -->|"writes labels"| node_pseudo_store
node_pseudo_store -.->|"pseudo-labeled data"| node_semi1
node_dataset -->|"labeled data"| node_semi1
node_semi1 -->|"trains"| node_architecture
node_semi1 -->|"saves checkpoint"| node_checkpoints
node_semi1 -.->|"writes metrics"| node_metrics
node_checkpoints -->|"loads model"| node_pseudo2
node_pseudo_store -->|"excludes Phase 1 labels"| node_pseudo2
node_dataset -->|"remaining images"| node_pseudo2
node_pseudo2 -->|"writes labels"| node_pseudo_store
node_pseudo_store -.->|"pseudo-labeled data"| node_semi2
node_semi2 -->|"trains"| node_architecture
node_semi2 -->|"saves checkpoint"| node_checkpoints
node_semi2 -->|"appends results"| node_log
node_dataset -->|"test set"| node_evaluation
node_checkpoints -->|"evaluates models"| node_evaluation
node_metrics -->|"plots histories"| node_curves
node_metrics -->|"plots histories"| node_single_curves
node_metrics -->|"searches values"| node_metric_search
node_master -.->|"invokes phase"| node_semi1
node_master -.->|"invokes phase"| node_pseudo2
node_master -.->|"invokes phase"| node_semi2
node_master -.->|"invokes plotting"| node_curves

click node_supervised "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/supervised_training_local.py"
click node_pseudo1 "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/pseudo_label_generation_phase1_local.py"
click node_semi1 "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/semisupervised_training_phase1_local.py"
click node_pseudo2 "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/pseudo_label_generation_phase2_local.py"
click node_semi2 "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/semisupervised_training_phase2_local.py"
click node_master "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/run_master_pipeline.py"
click node_evaluation "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/evaluate_all_phases.py"
click node_curves "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/generate_combined_loss_curves.py"
click node_single_curves "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/generate_loss_curves_local.py"
click node_metric_search "https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/find_85_90_metrics_local.py"
click node_log "https://github.com/anjanisu/dfutissuesegnet/blob/main/output.txt"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_supervised,node_architecture,node_semi1,node_semi2,node_master toneBlue
class node_pseudo1,node_pseudo2,node_dataset toneAmber
class node_checkpoints,node_pseudo_store,node_metrics,node_log toneMint
class node_evaluation,node_curves,node_single_curves,node_metric_search toneRose
class node_researcher toneIndigo
```

## Components

### Model training

- [Supervised training](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/supervised_training_local.py): `codx/supervised_training_local.py`
- **Segmentation model**
- [Phase 1 semi-supervised](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/semisupervised_training_phase1_local.py): `codx/semisupervised_training_phase1_local.py`
- [Phase 2 semi-supervised](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/semisupervised_training_phase2_local.py): `codx/semisupervised_training_phase2_local.py`
- [Pipeline launcher](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/run_master_pipeline.py): `codx/run_master_pipeline.py`

### Pseudo-labeling

- [Phase 1 pseudo-labels](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/pseudo_label_generation_phase1_local.py): `codx/pseudo_label_generation_phase1_local.py`
- [Phase 2 pseudo-labels](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/pseudo_label_generation_phase2_local.py): `codx/pseudo_label_generation_phase2_local.py`

### Models and results

- **Model checkpoints**
- **Pseudo-label files**
- **Training metrics**
- [Phase results log](https://github.com/anjanisu/dfutissuesegnet/blob/main/output.txt): `output.txt`

### Evaluation and diagnostics

- [Phase evaluation](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/evaluate_all_phases.py): `codx/evaluate_all_phases.py`
- [Combined loss curves](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/generate_combined_loss_curves.py): `codx/generate_combined_loss_curves.py`
- [Per-run loss curves](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/generate_loss_curves_local.py): `codx/generate_loss_curves_local.py`
- [Metric search](https://github.com/anjanisu/dfutissuesegnet/blob/main/codx/find_85_90_metrics_local.py): `codx/find_85_90_metrics_local.py`

### Other components

- **Researcher**
- **DFUTissue data**

## Connections

- Researcher → Pipeline launcher: starts (evidence: `README.md`)
- DFUTissue data → Supervised training: labeled images (evidence: `README.md`)
- Supervised training → Segmentation model: trains (evidence: `README.md`)
- Supervised training → Model checkpoints: saves checkpoint (evidence: `codx/supervised_training_local.py`)
- Supervised training → Training metrics: writes metrics (evidence: `codx/supervised_training_local.py`)
- Model checkpoints → Phase 1 pseudo-labels: loads model (evidence: `codx/pseudo_label_generation_phase1_local.py`)
- DFUTissue data → Phase 1 pseudo-labels: unlabeled images (evidence: `codx/pseudo_label_generation_phase1_local.py`)
- Phase 1 pseudo-labels → Pseudo-label files: writes labels (evidence: `codx/pseudo_label_generation_phase1_local.py`)
- Pseudo-label files → Phase 1 semi-supervised: pseudo-labeled data (evidence: `README.md`)
- DFUTissue data → Phase 1 semi-supervised: labeled data (evidence: `codx/semisupervised_training_phase1_local.py`)
- Phase 1 semi-supervised → Segmentation model: trains (evidence: `README.md`)
- Phase 1 semi-supervised → Model checkpoints: saves checkpoint (evidence: `codx/semisupervised_training_phase1_local.py`)
- Phase 1 semi-supervised → Training metrics: writes metrics (evidence: `README.md`)
- Model checkpoints → Phase 2 pseudo-labels: loads model (evidence: `codx/pseudo_label_generation_phase2_local.py`)
- Pseudo-label files → Phase 2 pseudo-labels: excludes Phase 1 labels (evidence: `codx/pseudo_label_generation_phase2_local.py`)
- DFUTissue data → Phase 2 pseudo-labels: remaining images (evidence: `codx/pseudo_label_generation_phase2_local.py`)
- Phase 2 pseudo-labels → Pseudo-label files: writes labels (evidence: `codx/pseudo_label_generation_phase2_local.py`)
- Pseudo-label files → Phase 2 semi-supervised: pseudo-labeled data (evidence: `README.md`)
- Phase 2 semi-supervised → Segmentation model: trains (evidence: `README.md`)
- Phase 2 semi-supervised → Model checkpoints: saves checkpoint (evidence: `codx/semisupervised_training_phase2_local.py`)
- Phase 2 semi-supervised → Phase results log: appends results (evidence: `codx/semisupervised_training_phase2_local.py`)
- DFUTissue data → Phase evaluation: test set (evidence: `codx/evaluate_all_phases.py`)
- Model checkpoints → Phase evaluation: evaluates models (evidence: `codx/evaluate_all_phases.py`)
- Training metrics → Combined loss curves: plots histories (evidence: `codx/generate_combined_loss_curves.py`)
- Training metrics → Per-run loss curves: plots histories (evidence: `codx/generate_loss_curves_local.py`)
- Training metrics → Metric search: searches values (evidence: `codx/find_85_90_metrics_local.py`)
- Pipeline launcher → Phase 1 semi-supervised: invokes phase (evidence: `codx/run_master_pipeline.py`)
- Pipeline launcher → Phase 2 pseudo-labels: invokes phase (evidence: `codx/run_master_pipeline.py`)
- Pipeline launcher → Phase 2 semi-supervised: invokes phase (evidence: `codx/run_master_pipeline.py`)
- Pipeline launcher → Combined loss curves: invokes plotting (evidence: `codx/run_master_pipeline.py`)
