CIFAR-10 Image Classifier

This model classifies images into 10 categories using a Convolutional Neural Network (CNN).

Model Description

Architecture: Custom CNN with 3 convolutional blocks
Dataset: CIFAR-10 (60,000 32x32 color images)
Classes: airplane, car, bird, cat, deer, dog, frog, horse, ship, truck
Test Accuracy: 79.35%

Usage

import torch
from PIL import Image
import torchvision.transforms as transforms

# Load model
model = torch.load('cifar10_cnn.pth')
model.eval()

# Prepare image
transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

img = Image.open('your_image.jpg')
img_tensor = transform(img).unsqueeze(0)

# Predict
with torch.no_grad():
    output = model(img_tensor)
    predicted_class = output.argmax(dim=1).item()

Training

Epochs: 15
Optimizer: Adam
Learning Rate: 0.001
Batch Size: 32

License

This model is released under the MIT License.

Downloads last month: -; Downloads are not tracked for this model. How to track