# gt-610/cv-lab-gtsrb architecture

> Architecture diagram of the GitHub repository gt-610/cv-lab-gtsrb, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-22). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/gt-610/cv-lab-gtsrb
- Repository: https://github.com/gt-610/cv-lab-gtsrb

## Overview

This is a GTSRB traffic-sign recognition course project: users can inspect the dataset, train and evaluate classifiers, predict signs from images, compare integrated member-B models, and run a Streamlit demo. The main workflow is config-driven training over GTSRB data through model creation and training, producing checkpoints and evaluation artifacts. The graph also preserves analysis, result summarization, demo-asset preparation, and B-model artifact preparation. Edges follow shown calls, source-index references, or README statements; unsampled script internals are not assumed.

Main entry points: [`scripts/eval_model.py`](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/eval_model.py) (Evaluation entrypoint), [`scripts/train_model.py`](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/train_model.py) (Train entrypoint), [`src/cvlab/train.py`](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/train.py) (Training engine), [`src/cvlab/utils.py`](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/utils.py) (Runtime utilities)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_workflow["Training and Evaluation"]
  node_train_entry["Train entrypoint<br/>[train_model.py]"]
  node_train_config["Training configs<br/>[resnet18.yaml]"]
  node_evaluation_entry["Evaluation entrypoint<br/>[eval_model.py]"]
end

subgraph group_runtime["Prediction and Demo"]
  node_image_prediction["Single-image prediction<br/>[predict_image.py]"]
  node_streamlit_demo["Interactive demo<br/>[demo_streamlit.py]"]
end

subgraph group_analysis["Dataset and Results"]
  node_dataset_analysis["Dataset analysis<br/>[analyze_dataset.py]"]
  node_result_summary["Experiment summaries"]
  node_demo_assets["Demo asset preparation"]
end

subgraph group_memberb["Member B Models"]
  node_b_predictor["Member B predictors<br/>[b_models.py]"]
  node_all_models["Multi-model prediction"]
  node_b_artifacts["B artifact preparation"]
end

subgraph group_shared["Shared ML Components"]
  node_dataset["GTSRB data loaders<br/>[data.py]"]
  node_class_labels["Class labels<br/>[labels.py]"]
  node_classifier["Classifier models<br/>[models.py]"]
  node_trainer["Training engine<br/>[train.py]"]
  node_metrics["Classification metrics<br/>[metrics.py]"]
  node_visualization["Training visualizations<br/>[visualize.py]"]
  node_utilities["Runtime utilities<br/>[utils.py]"]
end

node_engineer(("Project user"))

node_engineer -->|"starts training"| node_train_entry
node_train_config -->|"configures"| node_train_entry
node_train_entry -->|"builds loaders"| node_dataset
node_train_entry -->|"creates model"| node_classifier
node_train_entry -->|"runs training"| node_trainer
node_dataset -->|"uses labels"| node_class_labels
node_trainer -->|"computes metrics"| node_metrics
node_trainer -->|"plots results"| node_visualization
node_trainer -->|"writes run data"| node_utilities
node_engineer -->|"starts evaluation"| node_evaluation_entry
node_evaluation_entry -->|"builds loaders"| node_dataset
node_evaluation_entry -->|"loads checkpoint"| node_classifier
node_evaluation_entry -->|"evaluates model"| node_trainer
node_evaluation_entry -->|"builds confusion matrix"| node_metrics
node_evaluation_entry -->|"plots evaluation"| node_visualization
node_engineer -->|"analyzes dataset"| node_dataset_analysis
node_dataset_analysis -->|"uses labels"| node_class_labels
node_dataset_analysis -->|"creates output directory"| node_utilities
node_engineer -->|"summarizes results"| node_result_summary
node_result_summary -->|"uses utilities"| node_utilities
node_engineer -->|"prepares assets"| node_demo_assets
node_demo_assets -->|"uses labels"| node_class_labels
node_demo_assets -->|"uses utilities"| node_utilities
node_engineer -->|"predicts image"| node_image_prediction
node_image_prediction -->|"loads model"| node_classifier
node_engineer -->|"uses demo"| node_streamlit_demo
node_streamlit_demo -->|"loads checkpoint model"| node_classifier
node_engineer -->|"prepares artifacts"| node_b_artifacts
node_engineer -->|"runs model comparison"| node_all_models
node_all_models -->|"runs predictions"| node_b_predictor
node_b_predictor -->|"uses labels"| node_class_labels
node_b_predictor -->|"selects device"| node_utilities

click node_train_entry "https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/train_model.py"
click node_train_config "https://github.com/gt-610/cv-lab-gtsrb/blob/main/configs/resnet18.yaml"
click node_dataset "https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/data.py"
click node_class_labels "https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/labels.py"
click node_classifier "https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/models.py"
click node_trainer "https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/train.py"
click node_metrics "https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/metrics.py"
click node_visualization "https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/visualize.py"
click node_utilities "https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/utils.py"
click node_evaluation_entry "https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/eval_model.py"
click node_dataset_analysis "https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/analyze_dataset.py"
click node_result_summary "https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/summarize_results.py"
click node_demo_assets "https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/prepare_demo_assets.py"
click node_image_prediction "https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/predict_image.py"
click node_streamlit_demo "https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/demo_streamlit.py"
click node_b_predictor "https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/b_models.py"
click node_all_models "https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/predict_all_models.py"
click node_b_artifacts "https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/prepare_b_artifacts.py"

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_train_entry,node_train_config,node_evaluation_entry,node_engineer toneBlue
class node_image_prediction,node_streamlit_demo toneAmber
class node_dataset_analysis,node_result_summary,node_demo_assets toneMint
class node_b_predictor,node_all_models,node_b_artifacts toneRose
class node_dataset,node_class_labels,node_classifier,node_trainer,node_metrics,node_visualization,node_utilities toneIndigo
```

## Components

### Training and Evaluation

- [Train entrypoint](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/train_model.py): `scripts/train_model.py`
- [Training configs](https://github.com/gt-610/cv-lab-gtsrb/blob/main/configs/resnet18.yaml): `configs/resnet18.yaml`
- [Evaluation entrypoint](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/eval_model.py): `scripts/eval_model.py`

### Prediction and Demo

- [Single-image prediction](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/predict_image.py): `scripts/predict_image.py`
- [Interactive demo](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/demo_streamlit.py): `scripts/demo_streamlit.py`

### Dataset and Results

- [Dataset analysis](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/analyze_dataset.py): `scripts/analyze_dataset.py`
- [Experiment summaries](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/summarize_results.py): `scripts/summarize_results.py`
- [Demo asset preparation](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/prepare_demo_assets.py): `scripts/prepare_demo_assets.py`

### Member B Models

- [Member B predictors](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/b_models.py): `src/cvlab/b_models.py`
- [Multi-model prediction](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/predict_all_models.py): `scripts/predict_all_models.py`
- [B artifact preparation](https://github.com/gt-610/cv-lab-gtsrb/blob/main/scripts/prepare_b_artifacts.py): `scripts/prepare_b_artifacts.py`

### Shared ML Components

- [GTSRB data loaders](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/data.py): `src/cvlab/data.py`
- [Class labels](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/labels.py): `src/cvlab/labels.py`
- [Classifier models](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/models.py): `src/cvlab/models.py`
- [Training engine](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/train.py): `src/cvlab/train.py`
- [Classification metrics](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/metrics.py): `src/cvlab/metrics.py`
- [Training visualizations](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/visualize.py): `src/cvlab/visualize.py`
- [Runtime utilities](https://github.com/gt-610/cv-lab-gtsrb/blob/main/src/cvlab/utils.py): `src/cvlab/utils.py`

### Other components

- **Project user**

## Connections

- Project user → Train entrypoint: starts training (evidence: `README.md`)
- Training configs → Train entrypoint: configures (evidence: `README.md`)
- Train entrypoint → GTSRB data loaders: builds loaders (evidence: `scripts/train_model.py`)
- Train entrypoint → Classifier models: creates model (evidence: `scripts/train_model.py`)
- Train entrypoint → Training engine: runs training (evidence: `scripts/train_model.py`)
- GTSRB data loaders → Class labels: uses labels (evidence: `src/cvlab/data.py`)
- Training engine → Classification metrics: computes metrics (evidence: `src/cvlab/train.py`)
- Training engine → Training visualizations: plots results (evidence: `src/cvlab/train.py`)
- Training engine → Runtime utilities: writes run data (evidence: `src/cvlab/train.py`)
- Project user → Evaluation entrypoint: starts evaluation (evidence: `README.md`)
- Evaluation entrypoint → GTSRB data loaders: builds loaders (evidence: `scripts/eval_model.py`)
- Evaluation entrypoint → Classifier models: loads checkpoint (evidence: `scripts/eval_model.py`)
- Evaluation entrypoint → Training engine: evaluates model (evidence: `scripts/eval_model.py`)
- Evaluation entrypoint → Classification metrics: builds confusion matrix (evidence: `scripts/eval_model.py`)
- Evaluation entrypoint → Training visualizations: plots evaluation (evidence: `scripts/eval_model.py`)
- Project user → Dataset analysis: analyzes dataset (evidence: `README.md`)
- Dataset analysis → Class labels: uses labels (evidence: `scripts/analyze_dataset.py`)
- Dataset analysis → Runtime utilities: creates output directory (evidence: `scripts/analyze_dataset.py`)
- Project user → Experiment summaries: summarizes results (evidence: `README.md`)
- Experiment summaries → Runtime utilities: uses utilities (evidence: `scripts/summarize_results.py`)
- Project user → Demo asset preparation: prepares assets (evidence: `README.md`)
- Demo asset preparation → Class labels: uses labels (evidence: `scripts/prepare_demo_assets.py`)
- Demo asset preparation → Runtime utilities: uses utilities (evidence: `scripts/prepare_demo_assets.py`)
- Project user → Single-image prediction: predicts image (evidence: `README.md`)
- Single-image prediction → Classifier models: loads model (evidence: `scripts/predict_image.py`)
- Project user → Interactive demo: uses demo (evidence: `README.md`)
- Interactive demo → Classifier models: loads checkpoint model (evidence: `scripts/demo_streamlit.py`)
- Project user → B artifact preparation: prepares artifacts (evidence: `README.md`)
- Project user → Multi-model prediction: runs model comparison (evidence: `README.md`)
- Multi-model prediction → Member B predictors: runs predictions (evidence: `scripts/predict_all_models.py`)
- Member B predictors → Class labels: uses labels (evidence: `src/cvlab/b_models.py`)
- Member B predictors → Runtime utilities: selects device (evidence: `src/cvlab/b_models.py`)
