# deepmancer/resnet-cifar-classification architecture

> Architecture diagram of the GitHub repository deepmancer/resnet-cifar-classification, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-29). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/deepmancer/resnet-cifar-classification
- Repository: https://github.com/deepmancer/resnet-cifar-classification

## Overview

This repository is a pair of notebook-based image-classification experiments. The documented primary workflow trains a from-scratch ResNet-18 on CIFAR-10, then examines penultimate-layer features with t-SNE and k-NN. The tree also contains a separate simple-CNN classification notebook. Source excerpts were not available, so the graph follows README-documented relationships and avoids asserting notebook-internal call order beyond those relationships.

Main entry points: [`ResNet-18/CIFAR10_Classification.ipynb`](https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb) (ResNet Notebook), [`Images`](https://github.com/deepmancer/resnet-cifar-classification/tree/master/Images) (Feature Visualizations), [`Simple_Conv/Image_Classification_CNN.ipynb`](https://github.com/deepmancer/resnet-cifar-classification/blob/master/Simple_Conv/Image_Classification_CNN.ipynb) (Simple CNN Notebook)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_experiments["Classification Experiments"]
  node_resnet_nb["ResNet Notebook"]
  node_simple_cnn_nb["Simple CNN Notebook"]
  node_cifar10[("CIFAR-10")]
  node_resnet["ResNet-18 Model"]
  node_simple_cnn["CNN Classifier"]
end

subgraph group_analysis["Feature Analysis"]
  node_feature_space["Penultimate Features"]
  node_tsne["t-SNE Projection"]
  node_knn["k-NN Analysis"]
end

subgraph group_outputs["Visual Outputs"]
  node_feature_images["Feature Visualizations"]
end

node_user(("Notebook User"))
node_pytorch["PyTorch"]

node_user -->|"runs"| node_resnet_nb
node_user -->|"runs"| node_simple_cnn_nb
node_resnet_nb -->|"trains on"| node_cifar10
node_resnet_nb -->|"implements and trains"| node_resnet
node_resnet_nb -->|"uses"| node_pytorch
node_resnet_nb -->|"explores"| node_feature_space
node_feature_space -->|"projects"| node_tsne
node_feature_space -->|"analyzes"| node_knn
node_tsne -->|"visualizes in"| node_feature_images
node_knn -->|"visualizes in"| node_feature_images

click node_resnet_nb "https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb"
click node_simple_cnn_nb "https://github.com/deepmancer/resnet-cifar-classification/blob/master/Simple_Conv/Image_Classification_CNN.ipynb"
click node_resnet "https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb"
click node_simple_cnn "https://github.com/deepmancer/resnet-cifar-classification/blob/master/Simple_Conv/Image_Classification_CNN.ipynb"
click node_feature_space "https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb"
click node_tsne "https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb"
click node_knn "https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb"
click node_feature_images "https://github.com/deepmancer/resnet-cifar-classification/tree/master/Images"

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_resnet_nb,node_simple_cnn_nb,node_cifar10,node_resnet,node_simple_cnn,node_user toneBlue
class node_feature_space,node_tsne,node_knn toneAmber
class node_feature_images toneMint
class node_pytorch toneIndigo
```

## Components

### Classification Experiments

- [ResNet Notebook](https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb): `ResNet-18/CIFAR10_Classification.ipynb`
- [Simple CNN Notebook](https://github.com/deepmancer/resnet-cifar-classification/blob/master/Simple_Conv/Image_Classification_CNN.ipynb): `Simple_Conv/Image_Classification_CNN.ipynb`
- **CIFAR-10**
- [ResNet-18 Model](https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb): `ResNet-18/CIFAR10_Classification.ipynb`
- [CNN Classifier](https://github.com/deepmancer/resnet-cifar-classification/blob/master/Simple_Conv/Image_Classification_CNN.ipynb): `Simple_Conv/Image_Classification_CNN.ipynb`

### Feature Analysis

- [Penultimate Features](https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb): `ResNet-18/CIFAR10_Classification.ipynb`
- [t-SNE Projection](https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb): `ResNet-18/CIFAR10_Classification.ipynb`
- [k-NN Analysis](https://github.com/deepmancer/resnet-cifar-classification/blob/master/ResNet-18/CIFAR10_Classification.ipynb): `ResNet-18/CIFAR10_Classification.ipynb`

### Visual Outputs

- [Feature Visualizations](https://github.com/deepmancer/resnet-cifar-classification/tree/master/Images): `Images`

### Other components

- **Notebook User**
- **PyTorch**

## Connections

- Notebook User → ResNet Notebook: runs
- Notebook User → Simple CNN Notebook: runs
- ResNet Notebook → CIFAR-10: trains on
- ResNet Notebook → ResNet-18 Model: implements and trains
- ResNet Notebook → PyTorch: uses
- ResNet Notebook → Penultimate Features: explores
- Penultimate Features → t-SNE Projection: projects
- Penultimate Features → k-NN Analysis: analyzes
- t-SNE Projection → Feature Visualizations: visualizes in
- k-NN Analysis → Feature Visualizations: visualizes in