---
license: mit
tags:
- image-classification
- mnist
- cnn
---

# MNIST CNN Classifier

This model is a Convolutional Neural Network trained on the MNIST dataset
to classify handwritten digits (0–9).

## Model Architecture
- 2 Convolutional layers
- ReLU activations
- Max pooling
- Fully connected classifier
- Dropout for regularization

## Usage

```python
from inference import load_model, predict
import numpy as np

model = load_model("mnist_cnn.pth")

image = np.zeros((28, 28))
prediction = predict(image, model)
print(prediction)