claudegoodies
Skill

pytorch-patterns

From affaan-m

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

Documents PyTorch conventions for device handling, seeding, model architecture, training/validation loops, and Dataset classes.

Use it when

  • Writing new PyTorch training scripts or model classes
  • Reviewing deep learning code for common mistakes
  • Debugging GPU memory or non-reproducible training runs
  • Setting up mixed-precision training with GradScaler

Skip it if

  • Not using PyTorch specifically
  • Reference/documentation only, no executable tooling or automation
  • Code snippets are truncated/partial in the source

Facts

Repository
affaan-m/ECC
Status
Actively maintained
Last commit
Source file
.kiro/skills/pytorch-patterns/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

# 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_s
View full source on GitHub →

Other skills