# dasotse/deeplearning architecture

> Architecture diagram of the GitHub repository dasotse/deeplearning, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-16). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dasotse/deeplearning
- Repository: https://github.com/dasotse/deeplearning

## Overview

A. Project Type and Purpose
##### This is an educational Deep Learning module with two layers
- A set of teaching notebooks (introductory → advanced) that guide students through AI, neural networks, and advanced topics.
- A final “Práctica Final” project: a hybrid CNN+metadata model to predict tourist POI engagement.

B. File Structure Analysis
##### Top-level
- README.md – project overview, goals, deliverables
- Proyecto.zip – bundled dataset and code scaffolding for the final exercise
- notebooks/ – sequential Jupyter notebooks organized into three folders:
- 1. Introducción
- 2. Redes Neuronales
- 3. Redes Neuronales Avanzadas (plus module_utils.py)

C. Key Insights from README
##### Data: Images + structured metadata + engagement metrics
3. Deliverables: reproducible notebook (+ requirements), PDF report, trained model, preprocessing scripts

##### Compute Environment
- Google Colab / Local Jupyter + GPU
- Dependencies (requirements.txt / environment.yml)
##### Data Ingestion & Storage
- Proyecto.zip → unzipped into folders: images/, metadata.csv, engagement.csv
##### Data Preparation & EDA
- Preprocessing scripts (module_utils.py and student scripts)
- Image transformations (resize, normalize)
- Metadata cleaning, feature encoding
##### Feature Extraction Pipelines
- Visual branch: CNN backbone (e.g., pre-trained model, custom layers)
- Contextual branch: MLP or embedding layers for metadata
##### Model Architecture
- Fusion layer combining CNN outputs + metadata embeddings
- Classifier head → high vs. low engagement
##### Training & Optimization
- Training loop (batch generation, loss & optimizer, callbacks)
- Anti-overfitting (dropout, early stopping)
##### Evaluation & Analysis
- Metrics calculation (accuracy, confusion matrix, ROC)
- Visualization notebooks for results
##### Outputs & Deliverables
- Final model weights (.h5 or .pt)
- Reproducible notebook(s) with seeded experiments
- Technical report (PDF)
- Utility scripts

E. Relationships and Data Flows
- Convergence into the Model component
- Feedback loop from Evaluation back to Training (hyperparameter tuning)

F. Architectural Patterns & Design Principles
- Pipeline/Layered architecture: clear separation of ingestion, preprocessing, modeling, evaluation
- Modularity: notebooks vs. utility scripts vs. data
- Reproducibility: environment files, random seeds, documented pipeline steps

##### External dependencies: Google Colab and Google Drive for dataset access.

H. Diagramming Guidelines
##### Decisions: e.g., “Transfer Learning CNN,” “One-hot encoding.”

I. Emphasis
– Don’t over-complicate: model the project as discrete stages (Ingest → Prep → Feature → Train → Evaluate → Deliver).

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% External Environment
    Colab(["Google Colab / Local Jupyter"]):::external
    Drive(["Google Drive"]):::external

    %% Teaching Notebooks Module
    subgraph "Teaching Notebooks" 
        direction TB
        Intro["Introductory Module"]:::teaching
        NN["Neural Networks Module"]:::teaching
        Adv["Advanced Neural Networks Module"]:::teaching
    end

    %% Final Project Pipeline
    subgraph "Final Project Pipeline"
        direction TB
        Ingest(["Data Ingestion & Storage"]):::data
        Prep(["Data Preparation & EDA"]):::process
        subgraph "Feature Extraction"
            direction TB
            Visual["Visual Branch (CNN)"]:::model
            Context["Contextual Branch (Metadata MLP)"]:::model
        end
        Fusion(["Fusion Layer"]):::model
        Train(["Training & Optimization"]):::process
        Eval(["Evaluation & Analysis"]):::process
        Outputs(["Outputs & Deliverables"]):::data
    end

    %% Connections
    Colab -->|"access dataset"| Drive
    Drive -->|"Proyecto.zip"| Ingest
    Ingest -->|"raw images, metadata, engagement"| Prep
    Prep -->|"preprocessed images"| Visual
    Prep -->|"encoded metadata"| Context
    Visual -->|"feature vectors"| Fusion
    Context -->|"embeddings"| Fusion
    Fusion -->|"combined features"| Train
    Train -->|"trained weights"| Eval
    Eval -->|"metrics, insights"| Outputs
    Eval -->|"tuning feedback"| Train

    %% Click Events
    click Intro "https://github.com/dasotse/deeplearning/blob/main/notebooks/1. Introducción"
    click NN "https://github.com/dasotse/deeplearning/blob/main/notebooks/2. Redes Neuronales"
    click Adv "https://github.com/dasotse/deeplearning/blob/main/notebooks/3. Redes Neuronales Avanzadas"
    click Prep "https://github.com/dasotse/deeplearning/blob/main/notebooks/3. Redes Neuronales Avanzadas/module_utils.py"
    click Drive "https://github.com/dasotse/deeplearning/blob/main/Proyecto.zip"
    click Colab "https://github.com/dasotse/deeplearning/blob/main/README.md"

    %% Styles
    classDef data fill:#caf0f8,stroke:#03045e,color:#03045e
    classDef process fill:#d8f3dc,stroke:#1b4332,color:#1b4332
    classDef model fill:#ffd8a8,stroke:#e85d04,color:#e85d04
    classDef external fill:#e0c3fc,stroke:#7209b7,color:#7209b7
    classDef teaching fill:#a2d2ff,stroke:#1d3557,color:#1d3557
```
