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.

Install to Claude Code

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