Computer Vision ด้วย PyTorch ในปี 2026: CNN, Transfer Learning และคำถามสัมภาษณ์

# cnn_architecture.py
import torch
import torch.nn as nn

class SimpleCNN(nn.Module):
    """Basic CNN for CIFAR-10 classification (32x32 RGB images, 10 classes)"""
    
    def __init__(self, num_classes: int = 10):
        super().__init__()
        # First conv block: 3 input channels (RGB) -> 32 feature maps
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 32, kernel_size=3, padding=1),  # Output: 32x32x32
            nn.BatchNorm2d(32),  # Normalize activations for stable training
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2)  # Output: 16x16x32
        )
        # Second conv block: increase depth for richer features
        self.conv2 = nn.Sequential(
            nn.Conv2d(32, 64, kernel_size=3, padding=1),  # Output: 16x16x64
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2)  # Output: 8x8x64
        )
        # Third conv block: capture high-level patterns
        self.conv3 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3, padding=1),  # Output: 8x8x128
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2)  # Output: 4x4x128
        )
        # Classifier head
        self.classifier = nn.Sequential(
            nn.Flatten(),
            nn.Linear(128 * 4 * 4, 256),
            nn.ReLU(inplace=True),
            nn.Dropout(0.5),  # Prevent overfitting
            nn.Linear(256, num_classes)
        )
    
    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.conv3(x)
        return self.classifier(x)

# train_cnn.py
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import datasets, transforms

# Data augmentation for training (reduces overfitting)
train_transform = transforms.Compose([
    transforms.RandomHorizontalFlip(p=0.5),
    transforms.RandomCrop(32, padding=4),  # Random crop with padding
    transforms.ColorJitter(brightness=0.2, contrast=0.2),
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465),  # CIFAR-10 mean
                         (0.2470, 0.2435, 0.2616))  # CIFAR-10 std
])

# No augmentation for validation (deterministic evaluation)
val_transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465),
                         (0.2470, 0.2435, 0.2616))
])

def train_model(model: nn.Module, epochs: int = 20) -> dict:
    """Train CNN with standard best practices"""
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    model = model.to(device)
    
    # Load CIFAR-10 dataset
    train_data = datasets.CIFAR10(root="./data", train=True, 
                                   download=True, transform=train_transform)
    val_data = datasets.CIFAR10(root="./data", train=False,
                                 transform=val_transform)
    
    # DataLoaders with num_workers for parallel loading
    train_loader = DataLoader(train_data, batch_size=128, shuffle=True,
                              num_workers=4, pin_memory=True)
    val_loader = DataLoader(val_data, batch_size=256, shuffle=False,
                            num_workers=4, pin_memory=True)
    
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.AdamW(model.parameters(), lr=1e-3, weight_decay=1e-4)
    scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=epochs)
    
    best_acc = 0.0
    for epoch in range(epochs):
        model.train()
        for images, labels in train_loader:
            images, labels = images.to(device), labels.to(device)
            optimizer.zero_grad()
            outputs = model(images)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
        
        scheduler.step()
        
        # Validation
        model.eval()
        correct, total = 0, 0
        with torch.no_grad():
            for images, labels in val_loader:
                images, labels = images.to(device), labels.to(device)
                outputs = model(images)
                _, predicted = outputs.max(1)
                total += labels.size(0)
                correct += predicted.eq(labels).sum().item()
        
        acc = 100. * correct / total
        best_acc = max(best_acc, acc)
        print(f"Epoch {epoch+1}/{epochs} - Val Acc: {acc:.2f}%")
    
    return {"best_accuracy": best_acc}

# transfer_learning.py
import torch
import torch.nn as nn
from torchvision import models
from torchvision.models import ResNet50_Weights, EfficientNet_B0_Weights

def create_transfer_model(
    model_name: str = "resnet50",
    num_classes: int = 10,
    freeze_backbone: bool = True
) -> nn.Module:
    """Create a pretrained model with custom classification head"""
    
    if model_name == "resnet50":
        # Load ResNet50 with ImageNet weights
        model = models.resnet50(weights=ResNet50_Weights.IMAGENET1K_V2)
        # Replace final fully connected layer
        in_features = model.fc.in_features  # 2048 for ResNet50
        model.fc = nn.Sequential(
            nn.Dropout(0.3),
            nn.Linear(in_features, num_classes)
        )
        
    elif model_name == "efficientnet_b0":
        # EfficientNet: better accuracy/compute tradeoff
        model = models.efficientnet_b0(weights=EfficientNet_B0_Weights.IMAGENET1K_V1)
        in_features = model.classifier[1].in_features  # 1280 for B0
        model.classifier = nn.Sequential(
            nn.Dropout(0.2),
            nn.Linear(in_features, num_classes)
        )
    
    if freeze_backbone:
        # Freeze all layers except classifier
        for name, param in model.named_parameters():
            if "fc" not in name and "classifier" not in name:
                param.requires_grad = False
    
    return model

def count_trainable_params(model: nn.Module) -> int:
    """Count parameters that will be updated during training"""
    return sum(p.numel() for p in model.parameters() if p.requires_grad)

# Example usage
model = create_transfer_model("resnet50", num_classes=5, freeze_backbone=True)
print(f"Trainable parameters: {count_trainable_params(model):,}")
# Output: ~10,245 (only classifier) vs ~25 million (full ResNet50)

# augmentation_strategies.py
import torch
import torchvision.transforms.v2 as T
from torchvision.transforms.v2 import functional as F

# Modern augmentation pipeline using torchvision v2 transforms
advanced_augmentation = T.Compose([
    T.RandomResizedCrop(224, scale=(0.8, 1.0)),  # Random crop and resize
    T.RandomHorizontalFlip(p=0.5),
    T.RandomVerticalFlip(p=0.1),  # Less common but useful for some domains
    T.RandomRotation(degrees=15),
    T.ColorJitter(brightness=0.3, contrast=0.3, saturation=0.3, hue=0.1),
    T.RandomAffine(degrees=0, translate=(0.1, 0.1)),  # Small translations
    T.GaussianBlur(kernel_size=3, sigma=(0.1, 2.0)),
    T.ToImage(),
    T.ToDtype(torch.float32, scale=True),
    T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

class CutOut:
    """Randomly mask out square regions of the image"""
    def __init__(self, n_holes: int = 1, length: int = 16):
        self.n_holes = n_holes
        self.length = length
    
    def __call__(self, img: torch.Tensor) -> torch.Tensor:
        h, w = img.shape[1], img.shape[2]
        mask = torch.ones_like(img)
        
        for _ in range(self.n_holes):
            y = torch.randint(0, h, (1,)).item()
            x = torch.randint(0, w, (1,)).item()
            y1 = max(0, y - self.length // 2)
            y2 = min(h, y + self.length // 2)
            x1 = max(0, x - self.length // 2)
            x2 = min(w, x + self.length // 2)
            mask[:, y1:y2, x1:x2] = 0
        
        return img * mask

def mixup_data(
    x: torch.Tensor,
    y: torch.Tensor,
    alpha: float = 0.4
) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, float]:
    """MixUp: blend two images and their labels"""
    lam = torch.distributions.Beta(alpha, alpha).sample().item()
    batch_size = x.size(0)
    index = torch.randperm(batch_size)
    
    mixed_x = lam * x + (1 - lam) * x[index]
    y_a, y_b = y, y[index]
    
    return mixed_x, y_a, y_b, lam

# deployment_export.py
import torch
from torchvision import models
from torchvision.models import ResNet18_Weights

def export_for_production(model: torch.nn.Module, save_path: str) -> None:
    """Export model to TorchScript for production deployment"""
    model.eval()  # Set to evaluation mode (disables dropout, uses running stats)
    
    # Create example input matching expected dimensions
    example_input = torch.randn(1, 3, 224, 224)
    
    # Method 1: Tracing (for models without control flow)
    traced_model = torch.jit.trace(model, example_input)
    traced_model.save(save_path.replace(".pt", "_traced.pt"))
    
    # Method 2: Scripting (handles if/else, loops)
    scripted_model = torch.jit.script(model)
    scripted_model.save(save_path.replace(".pt", "_scripted.pt"))
    
    # Verify outputs match
    with torch.no_grad():
        original_out = model(example_input)
        traced_out = traced_model(example_input)
        scripted_out = scripted_model(example_input)
    
    assert torch.allclose(original_out, traced_out, atol=1e-5)
    assert torch.allclose(original_out, scripted_out, atol=1e-5)
    print(f"Model exported successfully to {save_path}")

def optimize_for_inference(model_path: str) -> torch.jit.ScriptModule:
    """Load and optimize TorchScript model for inference"""
    model = torch.jit.load(model_path)
    
    # Optimize for inference (fuses operations, removes dropout)
    optimized = torch.jit.optimize_for_inference(model)
    
    return optimized

# Export ResNet18
model = models.resnet18(weights=ResNet18_Weights.IMAGENET1K_V1)
export_for_production(model, "resnet18_production.pt")