# ashishpatel26/skin-lesions-detection-deep-learning architecture

> Architecture diagram of the GitHub repository ashishpatel26/skin-lesions-detection-deep-learning, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-19). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ashishpatel26/skin-lesions-detection-deep-learning
- Repository: https://github.com/ashishpatel26/skin-lesions-detection-deep-learning

## Overview

##### Project type and purpose
- This is an open-source machine-learning research/experimentation project (not a production web app).
- Its goal is to classify skin lesions from dermatoscopic images using deep convolutional networks (baseline CNN, fine-tuned pretrained models, and an ensemble).

##### File structure
- Top-level:
- LICENSE
- README.md
- Project_Report.pdf
- images/ (dataset preview screenshots)
- Notebooks/ (each Notebook encapsulates one stage or experiment)
- Notebooks sub-folders:
- Skin_Cancer_EDA.ipynb: data ingestion & exploratory analysis
- Baseline_CNN.ipynb: training a simple CNN from scratch
- Fine_Tuning_*.ipynb: fine-tuning various pretrained architectures (VGG16, InceptionV3, InceptionResNet, DenseNet)
- Retraining_*.ipynb: full re-training on ImageNet weights
- Ensemble_Models.ipynb: combining best models into an ensemble

##### README for additional insights
- Describes the HAM10000 dataset as the source of images.
- Lists each notebook’s purpose in the pipeline.
- Mentions Keras 2.2.4/TensorFlow 1.11 and a known BatchNorm caveat.
- Presents final validation/test accuracies for each model variant.

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Data Ingestion & EDA
    subgraph "Data Ingestion & EDA"
        direction TB
        DS["HAM10000 Dataset"]:::data
        EDA["Data Processing & EDA\n(Jupyter Notebook)"]:::data
    end

    %% Model Training Modules
    subgraph "Model Training Modules"
        direction TB
        Baseline["Baseline CNN Training"]:::model
        FT_VGG["Fine-Tuning VGG16"]:::model
        FT_InceptV3["Fine-Tuning InceptionV3"]:::model
        FT_ResNet["Fine-Tuning InceptionResNet"]:::model
        FT_Dense["Fine-Tuning DenseNet"]:::model
        RT_IncepV3["Full Retraining InceptionV3"]:::model
        RT_Dense["Full Retraining DenseNet"]:::model
    end

    %% Ensemble & Evaluation
    subgraph "Ensemble & Evaluation"
        direction TB
        Ensemble["Ensemble Module"]:::ensemble
        Eval["Evaluation & Reporting\n(Project_Report.pdf)"]:::ensemble
    end

    %% Infrastructure & Docs
    subgraph "Infrastructure & Documentation"
        direction TB
        Repo["README.md\n(Dependencies & Setup)"]:::infra
        License["LICENSE"]:::infra
    end

    %% Connections
    DS -->|"provides images"| EDA
    EDA -->|"outputs preprocessed data"| Baseline
    EDA --> FT_VGG
    EDA --> FT_InceptV3
    EDA --> FT_ResNet
    EDA --> FT_Dense
    EDA --> RT_IncepV3
    EDA --> RT_Dense

    Baseline -->|"checkpoints & logs"| Ensemble
    FT_VGG --> Ensemble
    FT_InceptV3 --> Ensemble
    FT_ResNet --> Ensemble
    FT_Dense --> Ensemble
    RT_IncepV3 --> Ensemble
    RT_Dense --> Ensemble

    Ensemble -->|"ensemble predictions"| Eval

    %% Documentation links
    Eval --> Repo
    Repo --> License

    %% Click Events
    click DS "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/tree/main/images/"
    click EDA "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Notebooks/Skin_Cancer_EDA.ipynb"
    click Baseline "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Notebooks/Baseline_CNN.ipynb"
    click FT_VGG "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Notebooks/Fine_Tuning_VGG16.ipynb"
    click FT_InceptV3 "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Notebooks/Fine_Tuning_InceptionV3.ipynb"
    click FT_ResNet "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Notebooks/Fine_Tuning_InceptionResNet.ipynb"
    click FT_Dense "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Notebooks/Fine_Tuning_DenseNet.ipynb"
    click RT_IncepV3 "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Notebooks/Retraining_InceptionV3.ipynb"
    click RT_Dense "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Notebooks/Retraining_DenseNet.ipynb"
    click Ensemble "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Notebooks/Ensemble_Models.ipynb"
    click Eval "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/Project_Report.pdf"
    click Repo "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/blob/main/README.md"
    click License "https://github.com/ashishpatel26/skin-lesions-detection-deep-learning/tree/main/LICENSE"

    %% Styles
    classDef data fill:#cfe2f3,stroke:#2a6f97
    classDef model fill:#d9ead3,stroke:#6aa84f
    classDef ensemble fill:#ffe599,stroke:#b07e1c
    classDef infra fill:#f0f0f0,stroke:#888888,stroke-dasharray: 5 5
```
