# sahilkatiyar17/deep_learning_practicals architecture

> Architecture diagram of the GitHub repository sahilkatiyar17/deep_learning_practicals, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-06-24). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sahilkatiyar17/deep_learning_practicals
- Repository: https://github.com/sahilkatiyar17/deep_learning_practicals

## Overview

##### Project type and purpose
- This is a collection of Jupyter notebooks for deep‐learning practicals.
- Purpose: explore image classification (Cats vs Dogs), data augmentation, transfer-learning (feature extraction and fine-tuning) with and without augmentation.

##### File structure
- All files are notebooks (.ipynb).
- No “src” folder or standalone scripts; the code lives in the notebooks themselves.
- Key notebooks:
- Cat-V-Dogs.ipynb (base classification)
- Data_augmentation.ipynb (augmenting images)
- Transfer-learning-feature-extraction…(with and without augmentation)
- transfer_learning_finetuning…
- No explicit config or deployment files—this is a self-contained exploratory repo.

##### README
- Confirms the repo is for deep-learning learning exercises.
- No additional architecture details or external services specified.

a. Main components:
1. Jupyter Notebook Environment
2. Data Source (local dataset or Kaggle Cats vs Dogs)
3. Preprocessing Pipelines
– Data Loader
– Data Augmentation Module
4. Model Training Modules
– Base CNN (from scratch)
– Feature-Extraction Model (pretrained backbone)
– Fine-Tuning Model (pretrained backbone + head)
5. Evaluation & Visualization
6. Artifacts Storage (trained model weights, logs, plots)
b. Relationships & Interactions:
1. Jupyter Notebook calls Data Loader → fetch raw images
2. Raw images → Preprocessing / Augmentation → Batches
3. Batches fed into Model Training modules
4. Models output metrics & checkpoints to Artifacts Storage
5. Notebook reads checkpoints for Evaluation & Visualization
c. Architectural patterns / design principles:
- Pipeline pattern for preprocessing → training → evaluation
- Reusability: augmentation logic used across multiple notebooks
- Layered approach: separate concerns (data, model logic, evaluation)
d. Technologies / libraries:
- Python 3.x, Jupyter Notebook
- TensorFlow or PyTorch (depending on implementation)
- torchvision or keras.preprocessing.image for augmentation
- Matplotlib / Seaborn for plots
- (Optional) Kaggle API if data downloaded programmatically

- Base CNN Training
- Pretrained Feature Extraction
- Pretrained Fine-Tuning
7. Callouts listing the primary libraries used at each stage.

## Diagram (Mermaid)

```mermaid
flowchart TB
    JNB["Jupyter Notebook Environment"]:::notebook
    DOC["Project Overview / Documentation (README.md)"]:::doc
    DS["Data Source (Local / Kaggle)"]:::data
    DL["Raw Data Loader"]:::process
    AUG["Data Augmentation Module"]:::process
    subgraph "Model Training Modules"
        BC["Base CNN Training"]:::notebook
        FE_AUG["Feature Extraction (with Augmentation)"]:::notebook
        FE_NOAUG["Feature Extraction (without Augmentation)"]:::notebook
        FT["Fine-Tuning (with/without Augmentation)"]:::notebook
    end
    ART["Artifacts Storage (models, logs, plots)"]:::data
    EV["Evaluation & Visualization"]:::process

    JNB --> DOC
    JNB --> DS
    DS --> DL
    DS --> AUG
    DL --> BC
    DL --> FE_AUG
    DL --> FE_NOAUG
    DL --> FT
    AUG -.-> FE_AUG
    AUG -.-> FT
    BC --> ART
    FE_AUG --> ART
    FE_NOAUG --> ART
    FT --> ART
    ART --> EV
    EV --> JNB

    click JNB "https://github.com/sahilkatiyar17/deep_learning_practicals/tree/main/./"
    click BC "https://github.com/sahilkatiyar17/deep_learning_practicals/blob/main/Cat-V-Dogs.ipynb"
    click AUG "https://github.com/sahilkatiyar17/deep_learning_practicals/blob/main/Data_augmentation.ipynb"
    click FE_AUG "https://github.com/sahilkatiyar17/deep_learning_practicals/blob/main/Transfer-learning-feature-extraction(data-augmentation).ipynb"
    click FE_NOAUG "https://github.com/sahilkatiyar17/deep_learning_practicals/blob/main/transfer_learning-feature-extraction(without-data-augmentation).ipynb"
    click FT "https://github.com/sahilkatiyar17/deep_learning_practicals/blob/main/transfer_learning_finetuning(with_and_without_data_augmentation.ipynb)"
    click DOC "https://github.com/sahilkatiyar17/deep_learning_practicals/blob/main/README.md"

    classDef notebook fill:#D0E6FF,stroke:#1f77b4,color:#000;
    classDef data fill:#CCFFCC,stroke:#2ca02c,color:#000;
    classDef process fill:#FFD099,stroke:#ff7f0e,color:#000;
    classDef doc fill:#F0F0F0,stroke:#7f7f7f,color:#000;
```
