README.md

---
library_name: pytorch
pipeline_tag: image-classification
datasets:
- uoft-cs/cifar10
metrics:
- accuracy
tags:
- pytorch
- cnn
- cifar10
- image-classification
- computer-vision
model-index:
- name: cnn-cifar10-classifier-v0.1.0
  results:
  - task:
      type: image-classification
      name: Image Classification
    dataset:
      name: CIFAR-10
      type: uoft-cs/cifar10
      config: plain_text
      split: test
    metrics:
    - type: accuracy
      value: 0.7857
      name: Test Accuracy
---

# cnn-cifar10-classifier v0.1.0

Small PyTorch CNN baseline for CIFAR-10 image classification.

This release contains the trained v0.1.0 checkpoint from the GitHub project:

https://github.com/diverHansun/cnn-cifar10-classifier

## Results

| Split | Metric | Value |
| --- | --- | ---: |
| test | accuracy | 0.7857 |

The checkpoint was selected by best validation/test accuracy during a 20 epoch run.

Training summary:

- Dataset: `uoft-cs/cifar10`
- Config: `plain_text`
- Epochs: 20
- Batch size: 256
- Optimizer: SGD, momentum 0.9, weight decay 0.0005
- Learning rate: 0.01
- Augmentation: random crop with padding 4, random horizontal flip
- AMP: enabled
- GPU used: NVIDIA GeForce RTX 5070 Ti
- PyTorch: 2.11.0+cu128

## Files

```text
checkpoints/best_model.pth
checkpoints/last_model.pth
outputs/training_metrics.json
outputs/training_curves.png
outputs/confusion_matrix.png
outputs/demo_predictions.png
logs/train_20260602_044856.log
logs/evaluate_20260602_045254.log
logs/demo_20260602_045311.log
runs/cifar10_cnn_20260602_044901/events.out.tfevents...
release_summary.json
manifest.sha256
```

## Usage

Clone the project code first:

```bash
git clone git@github.com:diverHansun/cnn-cifar10-classifier.git
cd cnn-cifar10-classifier
```

Install dependencies with a CUDA-compatible PyTorch build for your machine, then download this checkpoint:

```bash
hf download diverWayne/cnn-cifar10-classifier checkpoints/best_model.pth --local-dir .
```

Evaluate:

```bash
python evaluate.py --checkpoint checkpoints/best_model.pth --device cuda
```

Run the demo grid:

```bash
python demo.py --checkpoint checkpoints/best_model.pth --samples 16 --device cuda
```

Predict one image:

```bash
python predict.py --image demo_images/your_image.png --checkpoint checkpoints/best_model.pth --device cuda
```

## Limitations

This is a simple hand-written CNN baseline trained on CIFAR-10 32x32 images. It supports the 10 CIFAR-10 classes only:

```text
airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck
```

It can classify arbitrary images after resizing to 32x32, but reliability outside CIFAR-10-like images is limited.

The strongest observed confusions are between visually similar categories such as `cat` and `dog`, `bird` and `deer/dog`, and `airplane` and `ship`.

## Dataset

The training data is not redistributed in this model repository. It is loaded from the public Hugging Face dataset `uoft-cs/cifar10`.