lbernick/mnist-cnn

MNIST Teacher Model

A convolutional neural network trained on the MNIST dataset for handwritten digit classification.

Model Description

This is a ConvNet model trained on MNIST with the following architecture:

• Conv layer 1: 1 → 32 channels, 3x3 kernel
• ReLU + MaxPool (2x2)
• Conv layer 2: 32 → 64 channels, 3x3 kernel
• ReLU + MaxPool (2x2)
• Fully connected: 64 × 7 × 7 → 128 → 10 (output)

Training Details

Training Hyperparameters

• Batch size: 128
• Epochs: 10
• Learning rate: 0.001
• Weight decay: 0.0001
• Optimizer: AdamW
• Training set size: 50,000
• Validation set size: 10,000
• Test set size: 10,000
• Device: cuda
• Seed: 42

Results

• Test Accuracy: 0.9887
• Test Loss: 0.0402

Usage

import torch
from pathlib import Path

# Download the model
model_path = "model.pt"
state_dict = torch.load(model_path)

# Load into your ConvNet architecture
# (you'll need to define the ConvNet class from the training script)
model = ConvNet()
model.load_state_dict(state_dict)
model.eval()

# Make predictions
with torch.no_grad():
    predictions = model(images)

Dataset

The model was trained on the MNIST dataset, which contains 70,000 grayscale images of handwritten digits (0-9), each 28x28 pixels.

Model Card Authors

Generated automatically during training.