Pytorch Patterns

This one walks you through the PyTorch patterns that actually matter in production: device-agnostic code, proper reproducibility setup with seed management, explicit tensor shape tracking, and clean training loops with mixed precision support. It covers the full stack from nn.Module architecture (how to initialize weights correctly, when to use Sequential vs functional) to DataLoader optimization (pin_memory, persistent_workers) and proper checkpointing that saves optimizer state. The examples are opinionated about things like using set_to_none for gradient zeroing and @torch.no_grad() decorators. If you're moving past tutorials into real training pipelines or reviewing someone else's deep learning code, this gives you the patterns that prevent the common GPU memory bugs and reproducibility headaches.

skills.sh installs: 4.7K
GitHub stars: 229.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/everything-claude-code --skill pytorch-patterns --agent claude-code

Installs into .claude/skills of the current project.

Files

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.

# 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.

# 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

SKILL.md on GitHub