abir-hr196/cnn_transfer

MNIST CNN Model

This is a Convolutional Neural Network (CNN) trained on the MNIST dataset.

Model Details

• Architecture: CNN
• Dataset: MNIST
• Epochs: 10
• Batch Size: 128
• Learning Rate: 0.0003
• Random Seed: 42
• Best Validation Accuracy: 99.12%

How to Use

import torch
# Define your MNISTCNN class here or import it
# model = MNISTCNN()
# model.load_state_dict(torch.load('pytorch_model.bin', map_location='cpu'))
# model.eval()