kingkenche/stl10-resnet18

STL-10 ResNet-18 Classification Model

This model is a fine-tuned ResNet-18 for STL-10 image classification.

Model Details

• Base Model: ResNet-18 (pretrained on ImageNet)
• Dataset: STL-10 Subset
• Classes: 10
• Accuracy: 0.8400

Class Names

airplane, bird, car, cat, deer, dog, horse, monkey, ship, truck

Usage

import torch
from torchvision import transforms
from PIL import Image

# Load model (implement loading logic)
# model = load_model()

# Define transform
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

# Inference
image = Image.open("path/to/image.jpg")
input_tensor = transform(image).unsqueeze(0)
with torch.no_grad():
    outputs = model(input_tensor)
    predicted_class = torch.argmax(outputs, dim=1)