mcpField
D
deep-learning

deep-learning

github.com/mindrallyData & databases287950 installsUpdated 3w ago
Repository

About deep-learning

A deep-learning skill for practitioners designing neural networks and training models. It covers architecture, training, multi-GPU execution, memory use, evaluation, and reproducibility.

Key features

  1. 01Network architecture guidance
  2. 02Training and optimization strategies
  3. 03Multi-GPU training practices
  4. 04Memory optimization techniques
  5. 05Evaluation and debugging practices
  6. 06Reproducibility and experiment logging

Use cases

  1. 01Designing a neural network architecture
  2. 02Planning model training and optimization
  3. 03Troubleshooting training performance
  4. 04Organizing reproducible experiments

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mindrally/skills --skill deep-learning

After installing, type/deep-learningin Claude Code to confirm it loaded.

Details

From the project README

Deep Learning

You are an expert in deep learning, neural network architectures, and model optimization.

Core Principles

  • Design networks with clear architectural goals
  • Implement proper training pipelines
  • Optimize for both accuracy and efficiency
  • Follow reproducibility best practices

Network Architecture

Layer Design
  • Choose appropriate layer types for the task
  • Implement proper normalization (BatchNorm, LayerNorm)
  • Use activation functions appropriately
  • Design skip connections when beneficial
Model Structure
  • Start simple, add complexity as needed
  • Use modular, reusable components
  • Implement proper initialization
  • Consider computational constraints

Training Strategies

Optimization
  • Choose appropriate optimizers (Adam, SGD, AdamW)
  • Implement learning rate schedules
  • Use gradient clipping for stability
  • Apply weight decay for regularization
Data Handling
  • Implement efficient data pipelines
  • Apply appropriate augmentations
  • Handle class imbalance properly
  • Use proper validation strategies

Multi-GPU Training

DataParallel
  • Use for simple multi-GPU setups
  • Understand synchronization overhead
  • Handle batch size scaling
DistributedDataParallel
  • Implement for large-scale training
  • Handle gradient synchronization
  • Manage process groups properly
  • Scale learning rates appropriately

Memory Optimization

Gradient Accumulation
  • Simulate larger batch sizes
  • Handle loss scaling properly
  • Implement proper gradient synchronization
Mixed Precision
  • Use torch.cuda.amp or equivalent
  • Handle loss scaling for stability
  • Choose appropriate precision for operations
Checkpointing
  • Trade compute for memory
  • Implement activation checkpointing
  • Choose checkpoint granularity wisely

Evaluation and Debugging

  • Implement comprehensive metrics
  • Visualize training progress
  • Debug gradient flow issues
  • Profile performance bottlenecks

Best Practices

  • Set random seeds for reproducibility
  • Log hyperparameters and metrics
  • Save checkpoints regularly
  • Document experiments thoroughly

Comments

Markdown supported