CIFAR-10 ResNet18 Classifier
Ini adalah model ResNet18 yang dilatih pada dataset CIFAR-10 untuk klasifikasi gambar.
Model Details
- Architecture: ResNet18 (Pretrained)
- Dataset: CIFAR-10
- Classes: 10 (airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck)
- Input Size: 32x32 RGB images
Usage
import torch
from torchvision import models
from torchvision import transforms
Load model
model = models.resnet18()
model.fc = torch.nn.Linear(512, 10)
model.load_state_dict(torch.load('pytorch_model.bin'))
model.eval()
Prepare image
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.4914, 0.4822, 0.4465],
std=[0.2023, 0.1994, 0.2010])
])
Inference
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)
with torch.no_grad():
outputs = model(image.unsqueeze(0).to(device))
probabilities = torch.softmax(outputs, dim=1)
confidence, predicted = torch.max(probabilities, 1)
Performance
- Test Accuracy: Check model card for accuracy details
Author
Created as part of CNN Image Classification project
License
MIT
