skills.rest
HermeticOrmus
HermeticOrmusCOMMUNITY
Explore all skills by this author →
Website𝕏@dbodartmGitHub

PyTorch Patterns

Implement custom PyTorch datasets, modules, and autograd functions.

Updated Feb 25, 2026
Search Tags:#model training#deep learning#pytorch#ml engineering#data loading#neural networks
One-click install
npx skills add https://github.com/HermeticOrmus/LibreMLOps-Claude-Code --skill pytorch-patterns
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: PyTorch Patterns
Source: https://github.com/HermeticOrmus/LibreMLOps-Claude-Code/tree/main/plugins/pytorch-patterns/skills/pytorch-patterns
Command: npx skills add https://github.com/HermeticOrmus/LibreMLOps-Claude-Code --skill pytorch-patterns

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides expert patterns and best practices for building robust, efficient, and production-ready PyTorch models and data pipelines, addressing common pitfalls in deep learning development.

Core Features & Use Cases

  • Custom Datasets & DataLoaders: Implement advanced data loading with augmentation and weighted sampling for imbalanced datasets.
  • nn.Module Design: Structure PyTorch modules with proper parameter/buffer registration and weight initialization.
  • Model Surgery: Techniques for fine-tuning pre-trained models, including freezing backbones and progressive unfreezing.
  • Custom Autograd: Define custom backward passes for numerical stability or performance optimizations.
  • DataLoader Profiling: Benchmark data pipelines to ensure they are not a bottleneck during training.
  • Use Case: When developing a new image classification model, use the custom Dataset pattern to integrate Albumentations for data augmentation and WeightedRandomSampler to handle class imbalance, ensuring efficient and effective training.

Quick Start

Apply the PyTorch Patterns skill to create a custom Dataset with transforms and weighted sampling for an image classification task.

Frequently Asked Questions about PyTorch Patterns

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I handle class imbalance in PyTorch DataLoader for model training?▼

Handle class imbalance in PyTorch DataLoader by implementing custom Dataset patterns with a WeightedRandomSampler. This ensures minority classes are sampled more frequently during model training, improving deep learning performance on imbalanced datasets.

What is the best way to freeze and unfreeze layers when fine-tuning a pre-trained neural network?▼

The best way to fine-tune neural networks is using model surgery techniques like freezing backbones and progressive unfreezing. This modifies nn.Module structures dynamically during training to adapt pre-trained weights to new tasks efficiently.

Why is my PyTorch DataLoader a bottleneck during deep learning training?▼

Your PyTorch DataLoader is a bottleneck because data pipelines lack throughput profiling. Benchmarking DataLoader performance identifies data loading inefficiencies, ensuring custom Dataset implementations with augmentation do not stall model training.

When do I need custom autograd functions in PyTorch neural networks?▼

You need custom autograd functions in PyTorch neural networks when defining custom backward passes for numerical stability. This addresses specific deep learning mathematical edge cases that standard PyTorch autograd cannot compute accurately.

Does PyTorch nn.Module require explicit weight initialization for deep learning models?▼

PyTorch nn.Module requires explicit weight initialization to structure neural networks properly. Registering parameters and buffers with correct initialization ensures stable model training and prevents common anti-patterns in deep learning development.

Related Skills

Explore More Software Engineering Skills→
zero3041zero3041
1

pytorch-patterns

Review PyTorch code for optimization and reproducibility best practices.

Community
Advanced
gagan114662gagan114662

sparse-autoencoder-training

Train and analyze Sparse Autoencoders to decompose neural network activations into interpretable features.

Community
Advanced
evalstateevalstate

trl

Submit TRL training jobs on Hugging Face Jobs and convert models to GGUF.

Community
Advanced
tondevreltondevrel
19

pytorch-research

Implement custom Autograd functions and DDP for PyTorch research.

Community
Advanced