license: mit language:

• en library_name: pytorch pipeline_tag: image-classification tags:
• pytorch
• cnn
• lenet
• cifar10
• deep-learning
• computer-vision datasets:
• cifar10

LeNet-5 on CIFAR-10

A PyTorch implementation of the classic LeNet-5 architecture trained on the CIFAR-10 dataset.

Model Details

• Architecture: LeNet-5
• Framework: PyTorch
• Dataset: CIFAR-10
• Input Size: 3 × 32 × 32
• Classes: 10

CIFAR-10 Classes

Training

• Optimizer: Adam
• Learning Rate: 1e-3
• Loss Function: CrossEntropyLoss
• Epochs: 20
• Batch Size: 64

Performance

Model Files

• lenet5_cifar10.pth — Trained model weights

Load Model

import torch

model = LeNet5()
model.load_state_dict(torch.load("lenet5_cifar10.pth"))
model.eval()

Inference

with torch.no_grad():
    outputs = model(images)
    _, predicted = torch.max(outputs, 1)

Author

Ankit Bari

• GitHub: https://github.com/aijadugar
• Hugging Face: https://huggingface.co/aijadugar