CIFAR-10 पर CNN बनाना और प्रशिक्षित करना

import torchvision
import torchvision.transforms as transforms

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(
        mean=(0.4914, 0.4822, 0.4465),
        std=(0.2023, 0.1994, 0.2010)
    )
])

train_set = torchvision.datasets.CIFAR10(
    root='./data', train=True,
    download=True, transform=transform
)
print('Training images:', len(train_set))   # 50000
print('Image shape:', train_set[0][0].shape) # (3, 32, 32)

from torch.utils.data import DataLoader

train_loader = DataLoader(
    train_set,
    batch_size=128,
    shuffle=True,
    num_workers=2,
    pin_memory=True     # faster GPU transfer
)

# Peek at one batch
X_batch, y_batch = next(iter(train_loader))
print('Batch images:', X_batch.shape)   # (128, 3, 32, 32)
print('Batch labels:', y_batch.shape)   # (128,)

import torch.nn as nn

class CIFAR10Net(nn.Module):
    def __init__(self):
        super().__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 32, 3, padding=1), nn.BatchNorm2d(32), nn.ReLU(),
            nn.Conv2d(32, 32, 3, padding=1), nn.BatchNorm2d(32), nn.ReLU(),
            nn.MaxPool2d(2),           # 32->16
            nn.Conv2d(32, 64, 3, padding=1), nn.BatchNorm2d(64), nn.ReLU(),
            nn.Conv2d(64, 64, 3, padding=1), nn.BatchNorm2d(64), nn.ReLU(),
            nn.MaxPool2d(2),           # 16->8
            nn.Conv2d(64, 128, 3, padding=1), nn.BatchNorm2d(128), nn.ReLU(),
            nn.MaxPool2d(2),           # 8->4
        )
        self.classifier = nn.Sequential(
            nn.AdaptiveAvgPool2d((1, 1)),
            nn.Flatten(),
            nn.Linear(128, 10)
        )

    def forward(self, x):
        return self.classifier(self.features(x))

import torch
import torch.nn as nn
import torch.optim as optim

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = CIFAR10Net().to(device)

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(
    model.parameters(),
    lr=0.1,
    momentum=0.9,
    weight_decay=5e-4
)
scheduler = optim.lr_scheduler.CosineAnnealingLR(
    optimizer, T_max=50
)

total_params = sum(p.numel() for p in model.parameters())
print(f'Parameters: {total_params:,}')   # ~250,000

import torch

def train_epoch(model, loader, criterion, optimizer, device):
    model.train()
    total_loss, correct, total = 0.0, 0, 0
    for X, y in loader:
        X, y = X.to(device), y.to(device)
        optimizer.zero_grad()
        logits = model(X)
        loss = criterion(logits, y)
        loss.backward()
        optimizer.step()
        total_loss += loss.item() * X.size(0)
        correct += (logits.argmax(1) == y).sum().item()
        total += X.size(0)
    return total_loss / total, correct / total

import torch

def eval_epoch(model, loader, criterion, device):
    model.eval()
    total_loss, correct, total = 0.0, 0, 0
    with torch.no_grad():
        for X, y in loader:
            X, y = X.to(device), y.to(device)
            logits = model(X)
            loss = criterion(logits, y)
            total_loss += loss.item() * X.size(0)
            correct += (logits.argmax(1) == y).sum().item()
            total += X.size(0)
    return total_loss / total, correct / total

num_epochs = 50
best_val_acc = 0.0

for epoch in range(num_epochs):
    tr_loss, tr_acc = train_epoch(
        model, train_loader, criterion, optimizer, device)
    val_loss, val_acc = eval_epoch(
        model, val_loader, criterion, device)
    scheduler.step()

    print(f'Epoch {epoch+1:03d}: '
          f'tr_loss={tr_loss:.3f} tr_acc={tr_acc:.3f} '
          f'val_loss={val_loss:.3f} val_acc={val_acc:.3f}')

    if val_acc > best_val_acc:
        best_val_acc = val_acc
        torch.save(model.state_dict(), 'best_cifar10.pt')

import torchvision.transforms as transforms

train_transform = transforms.Compose([
    transforms.RandomCrop(32, padding=4),       # shift by 4px
    transforms.RandomHorizontalFlip(),           # mirror 50%
    transforms.ColorJitter(
        brightness=0.2, contrast=0.2,
        saturation=0.2, hue=0.1
    ),
    transforms.ToTensor(),
    transforms.Normalize(
        (0.4914, 0.4822, 0.4465),
        (0.2023, 0.1994, 0.2010)
    )
])

test_transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(
        (0.4914, 0.4822, 0.4465),
        (0.2023, 0.1994, 0.2010)
    )
])

# Typical CIFAR-10 accuracy milestones
milestones = {
    'Epoch 1':  'val_acc ~35%  (random = 10%)',
    'Epoch 5':  'val_acc ~60%  (basic patterns learned)',
    'Epoch 10': 'val_acc ~70%  (edges, textures)',
    'Epoch 20': 'val_acc ~78%  (object parts)',
    'Epoch 50': 'val_acc ~85%  (with augmentation)',
    'With ResNet18': 'val_acc ~93%',
    'State of art': 'val_acc ~99%  (huge ensembles)'
}
for epoch, note in milestones.items():
    print(f'{epoch}: {note}')

import torch

classes = ['airplane', 'auto', 'bird', 'cat', 'deer',
           'dog', 'frog', 'horse', 'ship', 'truck']

# Collect all predictions
all_preds, all_labels = [], []
model.eval()
with torch.no_grad():
    for X, y in test_loader:
        X = X.to(device)
        preds = model(X).argmax(1).cpu()
        all_preds.extend(preds.tolist())
        all_labels.extend(y.tolist())

# Per-class accuracy
for i, cls in enumerate(classes):
    mask = [l == i for l in all_labels]
    correct = sum(p == l for p, l in zip(all_preds, all_labels) if l == i)
    total = sum(mask)
    print(f'{cls}: {correct}/{total} = {correct/total:.1%}')

import torch

def mixup_batch(X, y, alpha=0.2, num_classes=10):
    lam = torch.distributions.Beta(alpha, alpha).sample()
    idx = torch.randperm(X.size(0))
    X_mix = lam * X + (1 - lam) * X[idx]
    # Soft labels: blend of one-hot vectors
    y_onehot = torch.zeros(X.size(0), num_classes)
    y_onehot.scatter_(1, y.unsqueeze(1), 1)
    y_onehot2 = y_onehot[idx]
    y_mix = lam * y_onehot + (1 - lam) * y_onehot2
    return X_mix, y_mix

# Use with soft-label cross entropy
# loss = -(y_mix * F.log_softmax(logits, dim=1)).sum(dim=1).mean()