# parthchande/deepsliced-5g architecture

> Architecture diagram of the GitHub repository parthchande/deepsliced-5g, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/parthchande/deepsliced-5g
- Repository: https://github.com/parthchande/deepsliced-5g

## Overview

##### Project type and purpose
- DeepSliced 5G is a proof-of-concept/demo for 5G network slicing using a deep learning model implemented in a Jupyter Notebook.
- It ingests raw and prefiltered network data, preprocesses it, trains/persists a TensorFlow/Keras model, and runs inference to suggest slice configurations.

##### File structure
- Top-level files (no subdirectories):
- 5G_Dataset_Network_Slicing_CRAWDAD_Shared.xlsx (raw dataset)
- filtereddata.txt (preprocessed numeric data)
- input_file.csv, test_file.csv (CSV variants)
- Main.ipynb (orchestrates the pipeline)
- README.md, LICENSE
- No backend/frontend separation; this is a single-pipeline AI demo.

##### README for additional insights
- Confirms a 4-stage flow: Data Preparation → Model Architecture → Training → Inference & Adaptation
- Uses TensorFlow/Keras inside a notebook, with pandas for preprocessing.

## Diagram (Mermaid)

```mermaid
flowchart TB
    subgraph "Data Layer"
        EXCEL(("5G_Dataset_Network_Slicing_CRAWDAD_Shared.xlsx")):::dataStore
        IN_CSV(("input_file.csv")):::dataStore
        TEST_CSV(("test_file.csv")):::dataStore
        FILTERED(("filtereddata.txt")):::dataStore
    end

    PRE["Data Preprocessor"]:::compute
    TRAIN["Model Trainer"]:::compute
    MODEL(("Trained Model (checkpoint)")):::artifact
    INFER["Inference & Adaptation"]:::compute
    REPORT["Visualization / Reporting"]:::compute

    EXCEL -->|reads raw data| PRE
    IN_CSV -->|reads CSV data| PRE
    TEST_CSV -->|reads CSV data| PRE
    PRE -->|outputs filtereddata.txt| FILTERED
    FILTERED -->|training input| TRAIN
    IN_CSV -->|optional training input| TRAIN
    TRAIN -->|saves model checkpoint| MODEL
    MODEL -->|loads model| INFER
    TEST_CSV -->|prediction input| INFER
    INFER -->|results| REPORT

    click EXCEL "https://github.com/parthchande/deepsliced-5g/blob/main/5G_Dataset_Network_Slicing_CRAWDAD_Shared.xlsx"
    click IN_CSV "https://github.com/parthchande/deepsliced-5g/blob/main/input_file.csv"
    click TEST_CSV "https://github.com/parthchande/deepsliced-5g/blob/main/test_file.csv"
    click FILTERED "https://github.com/parthchande/deepsliced-5g/blob/main/filtereddata.txt"
    click PRE "https://github.com/parthchande/deepsliced-5g/blob/main/Main.ipynb"
    click TRAIN "https://github.com/parthchande/deepsliced-5g/blob/main/Main.ipynb"
    click INFER "https://github.com/parthchande/deepsliced-5g/blob/main/Main.ipynb"
    click REPORT "https://github.com/parthchande/deepsliced-5g/blob/main/Main.ipynb"

    classDef dataStore fill:#ADD8E6,stroke:#000,stroke-width:1px
    classDef compute fill:#90EE90,stroke:#000,stroke-width:1px
    classDef artifact fill:#FFFF99,stroke:#000,stroke-width:1px
```
