cifar100-resnet18

ResNet-18 for CIFAR-100 Classification

This is a ResNet-18 model trained on the CIFAR-100 dataset for image classification.

Model Details

• Architecture: ResNet-18 (Residual Network with 18 layers)
• Parameters: 11,220,132
• Dataset: CIFAR-100 (100 classes, 50,000 training images, 10,000 test images)
• Input Size: 32x32 RGB images
• Output: 100 class probabilities

Training Details

Training Configuration

• Epochs: 50
• Batch Size: 128
• Optimizer: SGD with momentum (0.9)
• Learning Rate: 0.1 (initial) with Cosine Annealing scheduler
• Weight Decay: 5e-4
• Loss Function: Cross Entropy Loss

Data Augmentation

Training augmentations:

• Random Crop (32x32, padding=4)
• Random Horizontal Flip
• Normalization: mean=(0.5071, 0.4867, 0.4408), std=(0.2675, 0.2565, 0.2761)

Performance

• Test Accuracy: 75.84%
• Training Accuracy: 99.86% (final epoch)
• Validation Accuracy: 75.68% (final epoch)

CIFAR-100 Classes

The model can classify images into 100 classes:

apple, aquarium_fish, baby, bear, beaver, bed, bee, beetle, bicycle, bottle, 
bowl, boy, bridge, bus, butterfly, camel, can, castle, caterpillar, cattle, 
chair, chimpanzee, clock, cloud, cockroach, couch, crab, crocodile, cup, dinosaur, 
dolphin, elephant, flatfish, forest, fox, girl, hamster, house, kangaroo, keyboard, 
lamp, lawn_mower, leopard, lion, lizard, lobster, man, maple_tree, motorcycle, mountain, 
mouse, mushroom, oak_tree, orange, orchid, otter, palm_tree, pear, pickup_truck, pine_tree, 
plain, plate, poppy, porcupine, possum, rabbit, raccoon, ray, road, rocket, rose, sea, 
seal, shark, shrew, skunk, skyscraper, snail, snake, spider, squirrel, streetcar, 
sunflower, sweet_pepper, table, tank, telephone, television, tiger, tractor, train, 
trout, tulip, turtle, wardrobe, whale, willow_tree, wolf, woman, worm

Usage

Load the Model

import torch
import torch.nn as nn

# Define the model architecture
class BasicBlock(nn.Module):
    expansion = 1
    
    def __init__(self, in_channels, out_channels, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, 
                               stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3,
                               stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        
        self.shortcut = nn.Sequential()
        if stride != 1 or in_channels != self.expansion * out_channels:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_channels, self.expansion * out_channels,
                         kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(self.expansion * out_channels)
            )
    
    def forward(self, x):
        out = torch.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        out += self.shortcut(x)
        out = torch.relu(out)
        return out

class ResNet(nn.Module):
    def __init__(self, block, num_blocks, num_classes=100):
        super(ResNet, self).__init__()
        self.in_channels = 64
        
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
        self.linear = nn.Linear(512 * block.expansion, num_classes)
    
    def _make_layer(self, block, out_channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_channels, out_channels, stride))
            self.in_channels = out_channels * block.expansion
        return nn.Sequential(*layers)
    
    def forward(self, x):
        out = torch.relu(self.bn1(self.conv1(x)))
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = torch.nn.functional.avg_pool2d(out, 4)
        out = out.view(out.size(0), -1)
        out = self.linear(out)
        return out

def ResNet18():
    return ResNet(BasicBlock, [2, 2, 2, 2])

# Load model from Hugging Face Hub
from huggingface_hub import hf_hub_download

# Download the model file
model_path = hf_hub_download(repo_id="YOUR_USERNAME/cifar100-resnet18", filename="best_model.pth")

# Create model and load weights
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = ResNet18().to(device)
model.load_state_dict(torch.load(model_path, map_location=device))
model.eval()

Make Predictions

from PIL import Image
import torchvision.transforms as transforms

# Define transforms
transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor(),
    transforms.Normalize((0.5071, 0.4867, 0.4408), (0.2675, 0.2565, 0.2761))
])

# Load and preprocess image
image = Image.open('path/to/your/image.jpg')
image_tensor = transform(image).unsqueeze(0).to(device)

# Make prediction
with torch.no_grad():
    output = model(image_tensor)
    probabilities = torch.nn.functional.softmax(output, dim=1)
    predicted_class = output.argmax(1).item()
    confidence = probabilities[0][predicted_class].item()

# CIFAR-100 class names
cifar100_classes = [
    'apple', 'aquarium_fish', 'baby', 'bear', 'beaver', 'bed', 'bee', 'beetle',
    'bicycle', 'bottle', 'bowl', 'boy', 'bridge', 'bus', 'butterfly', 'camel',
    'can', 'castle', 'caterpillar', 'cattle', 'chair', 'chimpanzee', 'clock',
    'cloud', 'cockroach', 'couch', 'crab', 'crocodile', 'cup', 'dinosaur',
    'dolphin', 'elephant', 'flatfish', 'forest', 'fox', 'girl', 'hamster',
    'house', 'kangaroo', 'keyboard', 'lamp', 'lawn_mower', 'leopard', 'lion',
    'lizard', 'lobster', 'man', 'maple_tree', 'motorcycle', 'mountain', 'mouse',
    'mushroom', 'oak_tree', 'orange', 'orchid', 'otter', 'palm_tree', 'pear',
    'pickup_truck', 'pine_tree', 'plain', 'plate', 'poppy', 'porcupine',
    'possum', 'rabbit', 'raccoon', 'ray', 'road', 'rocket', 'rose', 'sea',
    'seal', 'shark', 'shrew', 'skunk', 'skyscraper', 'snail', 'snake', 'spider',
    'squirrel', 'streetcar', 'sunflower', 'sweet_pepper', 'table', 'tank',
    'telephone', 'television', 'tiger', 'tractor', 'train', 'trout', 'tulip',
    'turtle', 'wardrobe', 'whale', 'willow_tree', 'wolf', 'woman', 'worm'
]

print(f'Predicted class: {cifar100_classes[predicted_class]}')
print(f'Confidence: {confidence*100:.2f}%')

Files

• best_model.pth: Model weights with best validation accuracy
• cifar100_resnet18_complete.pth: Complete checkpoint including optimizer state and training history
• training_history.png: Training and validation curves
• predictions_visualization.png: Sample predictions

Training Code

The complete training code is available in the accompanying Jupyter notebook cifar100_resnet.ipynb.

Limitations

• The model is trained specifically for 32x32 images
• Performance may degrade on images significantly different from CIFAR-100 style
• Some classes (like lobster/crab, cup/bottle) are challenging to distinguish

Citation

If you use this model, please cite:

@misc{cifar100-resnet18,
  author = {Your Name},
  title = {ResNet-18 for CIFAR-100 Classification},
  year = {2025},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/YOUR_USERNAME/cifar100-resnet18}}
}

License

MIT License