pytorch-patterns

# PyTorch Development Patterns

Idiomatic PyTorch patterns and best practices for building robust, efficient, and reproducible deep learning applications.

## When to Activate

- Writing new PyTorch models or training scripts
- Reviewing deep learning code
- Debugging training loops or data pipelines
- Optimizing GPU memory usage or training speed
- Setting up reproducible experiments

## Core Principles

### 1. Device-Agnostic Code

Always write code that works on both CPU and GPU without hardcoding devices.

```python
# Good: Device-agnostic
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = MyModel().to(device)
data = data.to(device)

# Bad: Hardcoded device
model = MyModel().cuda()  # Crashes if no GPU
data = data.cuda()
```

### 2. Reproducibility First

Set all random seeds for reproducible results.

```python
# Good: Full reproducibility setup
def set_seed(seed: int = 42) -> None:
    torch.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    np.random.seed(seed)
    random.seed(seed)
    torch.backends.cudnn.deterministic = True
    torch.backends.cudnn.benchmark = False

# Bad: No seed control
model = MyModel()  # Different weights every run
```

### 3. Explicit Shape Management

Always document and verify tensor shapes.

```python
# Good: Shape-annotated forward pass
def forward(self, x: torch.Tensor) -> torch.Tensor:
    # x: (batch_size, channels, height, width)
    x = self.conv1(x)    # -> (batch_size, 32, H, W)
    x = self.pool(x)     # -> (batch_size, 32, H//2, W//2)
    x = x.view(x.size(0), -1)  # -> (batch_size, 32*H//2*W//2)
    return self.fc(x)    # -> (batch_size, num_classes)

# Bad: No shape tracking
def forward(self, x):
    x = self.conv1(x)
    x = self.pool(x)
    x = x.view(x.size(0), -1)  # What size is this?
    return self.fc(x)           # Will this even work?
```

## Model Architecture Patterns

### Clean nn.Module Structure

```python
# Good: Well-organized module
class ImageClassifier(nn.Module):
    def __init__(self, num_classes: int, dropout: float = 0.5) -> None:
        super().__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2),
        )
        self.classifier = nn.Sequential(
            nn.Dropout(dropout),
            nn.Linear(64 * 16 * 16, num_classes),
        )

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.features(x)
        x = x.view(x.size(0), -1)
        return self.classifier(x)

# Bad: Everything in forward
class ImageClassifier(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, x):
        x = F.conv2d(x, weight=self.make_weight())  # Creates weight each call!
        return x
```

### Proper Weight Initialization

```python
# Good: Explicit initialization
def _init_weights(self, module: nn.Module) -> None:
    if isinstance(module, nn.Linear):
        nn.init.kaiming_normal_(module.weight, mode="fan_out", nonlinearity="relu")
        if module.bias is not None:
            nn.init.zeros_(module.bias)
    elif isinstance(module, nn.Conv2d):
        nn.init.kaiming_normal_(module.weight, mode="fan_out", nonlinearity="relu")
    elif isinstance(module, nn.BatchNorm2d):
        nn.init.ones_(module.weight)
        nn.init.zeros_(module.bias)

model = MyModel()
model.apply(model._init_weights)
```

## Training Loop Patterns

### Standard Training Loop

```python
# Good: Complete training loop with best practices
def train_one_epoch(
    model: nn.Module,
    dataloader: DataLoader,
    optimizer: torch.optim.Optimizer,
    criterion: nn.Module,
    device: torch.device,
    scaler: torch.amp.GradScaler | None = None,
) -> float:
    model.train()  # Always set train mode
    total_loss = 0.0

    for batch_idx, (data, target) in enumerate(dataloader):
        data, target = data.to(device), target.to(device)

        optimizer.zero_grad(set_to_none=True)  # More efficient than zero_grad()

        # Mixed precision training
        with torch.amp.autocast("cuda", enabled=scaler is not None):
            output = model(data)
            loss = criterion(output, target)

        if scaler is not None:
            scaler.scale(loss).backward()
            scaler.unscale_(optimizer)
            torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
            scaler.step(optimizer)
            scaler.update()
        else:
            loss.backward()
            torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
            optimizer.step()

        total_loss += loss.item()

    return total_loss / len(dataloader)
```

### Validation Loop

```python
# Good: Proper evaluation
@torch.no_grad()  # More efficient than wrapping in torch.no_grad() block
def evaluate(
    model: nn.Module,
    dataloader: DataLoader,
    criterion: nn.Module,
    device: torch.device,
) -> tuple[float, float]:
    model.eval()  # Always set eval mode — disables dropout, uses running BN stats
    total_loss = 0.0
    correct = 0
    total = 0

    for data, target in dataloader:
        data, target = data.to(device), target.to(device)
        output = model(data)
        total_loss += criterion(output, target).item()
        correct += (output.argmax(1) == target).sum().item()
        total += target.size(0)

    return total_loss / len(dataloader), correct / total
```

## Data Pipeline Patterns

### Custom Dataset

```python
# Good: Clean Dataset with type hints
class ImageDataset(Dataset):
    def __init__(
        self,
        image_dir: str,
        labels: dict[str, int],
        transform: transforms.Compose | None = None,
    ) -> None:
        self.image_paths = list(Path(image_dir).glob("*.jpg"))
        self.labels = labels
        self.transform = transform

    def __len__(self) -> int:
        return len(self.image_paths)

    def __getitem__(self, idx: int) -> tuple[torch.Tenso