metadata
license: mit
tags:
- image-classification
- stl10
- resnet18
- pytorch
datasets:
- Chiranjeev007/STL-10_Subset
metrics:
- accuracy
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)