# ishanrai05/skin-cancer-prediction architecture

> Architecture diagram of the GitHub repository ishanrai05/skin-cancer-prediction, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-18). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ishanrai05/skin-cancer-prediction
- Repository: https://github.com/ishanrai05/skin-cancer-prediction

## Overview

This is a PyTorch workflow for classifying HAM10000 dermatoscopic images into seven lesion categories. The principal path is dataset preparation and lesion-aware splitting, image normalization and loading, ResNeXt training and validation, then validation-set evaluation and visual reporting. The README also describes a notebook-based way to run the code and sample-image and class-distribution views. The graph follows relationships visible in the excerpts or README; those views are included as documented capabilities, though their runtime wiring is not established by the excerpts.

Main entry points: [`main.py`](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/main.py) (Training CLI), [`train.py`](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/train.py) (Train and validate), [`utils.py`](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/utils.py) (Image dataset), [`read_data.py`](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/read_data.py) (Metadata and split)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data preparation"]
  node_split["Metadata and split<br/>[read_data.py]"]
  node_normalization["Image statistics<br/>[utils.py]"]
  node_dataset["Image dataset<br/>[utils.py]"]
end

subgraph group_learning["Model training"]
  node_model["ResNeXt classifier<br/>[main.py]"]
  node_training["Train and validate<br/>[train.py]"]
  node_metrics["Training meters<br/>[utils.py]"]
end

subgraph group_evaluation["Evaluation and views"]
  node_evaluation["Validation evaluation<br/>[main.py]"]
  node_plots["Confusion matrix<br/>[visualize.py]"]
  node_sample_view["Sample images<br/>[visualize.py]"]
  node_distribution_view["Class distribution<br/>[visualize.py]"]
end

subgraph group_interfaces["Run interfaces"]
  node_cli["Training CLI<br/>[main.py]"]
  node_notebook["Notebook workflow"]
end

node_user(("Researcher"))
node_ham["HAM10000 files"]

node_user -->|"starts training"| node_cli
node_user -->|"runs notebook"| node_notebook
node_ham -->|"provides metadata"| node_split
node_ham -->|"provides images"| node_normalization
node_cli -->|"requests split"| node_split
node_cli -->|"computes statistics"| node_normalization
node_cli -->|"constructs datasets"| node_dataset
node_dataset -->|"loads image files"| node_ham
node_cli -->|"configures classifier"| node_model
node_cli -->|"calls train and validate"| node_training
node_training -->|"runs forward passes"| node_model
node_training -->|"updates meters"| node_metrics
node_cli -->|"evaluates validation set"| node_evaluation
node_evaluation -->|"predicts labels"| node_model
node_evaluation -->|"plots confusion matrix"| node_plots
node_user -.->|"requests samples"| node_sample_view
node_user -.->|"requests counts"| node_distribution_view

click node_cli "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/main.py"
click node_notebook "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/notebook/skin-cancer-prediction.ipynb"
click node_split "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/read_data.py"
click node_normalization "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/utils.py"
click node_dataset "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/utils.py"
click node_model "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/main.py"
click node_training "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/train.py"
click node_metrics "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/utils.py"
click node_evaluation "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/main.py"
click node_plots "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/visualize.py"
click node_sample_view "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/visualize.py"
click node_distribution_view "https://github.com/ishanrai05/skin-cancer-prediction/blob/master/visualize.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_split,node_normalization,node_dataset toneBlue
class node_model,node_training,node_metrics toneAmber
class node_evaluation,node_plots,node_sample_view,node_distribution_view toneMint
class node_cli,node_notebook toneRose
class node_user,node_ham toneIndigo
```

## Components

### Data preparation

- [Metadata and split](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/read_data.py): `read_data.py`
- [Image statistics](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/utils.py): `utils.py`
- [Image dataset](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/utils.py): `utils.py`

### Model training

- [ResNeXt classifier](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/main.py): `main.py`
- [Train and validate](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/train.py): `train.py`
- [Training meters](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/utils.py): `utils.py`

### Evaluation and views

- [Validation evaluation](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/main.py): `main.py`
- [Confusion matrix](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/visualize.py): `visualize.py`
- [Sample images](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/visualize.py): `visualize.py`
- [Class distribution](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/visualize.py): `visualize.py`

### Run interfaces

- [Training CLI](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/main.py): `main.py`
- [Notebook workflow](https://github.com/ishanrai05/skin-cancer-prediction/blob/master/notebook/skin-cancer-prediction.ipynb): `notebook/skin-cancer-prediction.ipynb`

### Other components

- **Researcher**
- **HAM10000 files**

## Connections

- Researcher → Training CLI: starts training (evidence: `README.md`)
- Researcher → Notebook workflow: runs notebook (evidence: `README.md`)
- HAM10000 files → Metadata and split: provides metadata (evidence: `read_data.py`)
- HAM10000 files → Image statistics: provides images
- Training CLI → Metadata and split: requests split (evidence: `main.py`)
- Training CLI → Image statistics: computes statistics (evidence: `main.py`)
- Training CLI → Image dataset: constructs datasets (evidence: `main.py`)
- Image dataset → HAM10000 files: loads image files (evidence: `utils.py`)
- Training CLI → ResNeXt classifier: configures classifier (evidence: `main.py`)
- Training CLI → Train and validate: calls train and validate (evidence: `main.py`)
- Train and validate → ResNeXt classifier: runs forward passes (evidence: `train.py`)
- Train and validate → Training meters: updates meters (evidence: `train.py`)
- Training CLI → Validation evaluation: evaluates validation set (evidence: `main.py`)
- Validation evaluation → ResNeXt classifier: predicts labels (evidence: `main.py`)
- Validation evaluation → Confusion matrix: plots confusion matrix (evidence: `main.py`)
- Researcher → Sample images: requests samples (evidence: `README.md`)
- Researcher → Class distribution: requests counts (evidence: `README.md`)
