---
license: mit
language:
  - en
  - ru
tags:
  - pytorch
  - cnn
  - mnist
  - image-classification
  - handwritten-digit-recognition
pipeline_tag: image-classification
library_name: pytorch
---

# MNIST Drawing Recognizer

A lightweight CNN model for real-time handwritten digit recognition (0-9) with a PyQt5 drawing interface (see full project).

## Model Description

- **Architecture**: Simple CNN with 2 convolutional layers + fully connected layers
- **Framework**: PyTorch
- **Output**: Digit 0-9 + confidence score
- **Accuracy**: ~98.7% on MNIST test set

## Source Code

Full project: [Click here!](https://github.com/MathematicLove/qt-mnist-recognizer)

## Usage

```python
from huggingface_hub import hf_hub_download
import torch
from train import Net

model_path = hf_hub_download("monadayzek/mnist-drawing-recognizer", "mnist_cnn.pth")

model = Net().to('cpu')
model.load_state_dict(torch.load(model_path, map_location='cpu', weights_only=True))
model.eval()