pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. Use when writing or reviewing PyTorch training loops, model architectures, or data loading, or when a run will not reproduce.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- pytorch-patterns
- metadata
- { "origin": "ECC" }
- description
- PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. Use when writing or reviewing PyTorch training loops, model architectures, or data loading, or when a run will not reproduce.
03 SKILL.md 正文
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
# Bad: No seed control
model = MyModel() # Different weights every run
3. Explicit Shape Management
Always document and verify tensor shapes.
# Good: Shape-annotated forward pass
def forward(self, x: torch.Tensor) -> torch.Tensor:
# x: (batch_size, channels, height, width)
x = self.conv1(x) # -> (batch_size, 32, H, W)
x = self.pool(x) # -> (batch_size, 32, H//2, W//2)
x = x.view(x.size(0), -1) # -> (batch_size, 32*H//2*W//2)
return self.fc(x) # -> (batch_size, num_classes)
# Bad: No shape tracking
def forward(self, x):
x = self.conv1(x)
x = self.pool(x)
x = x.view(x.size(0), -1) # What size is this?
return self.fc(x) # Will this even work?
Model Architecture Patterns
Clean nn.Module Structure
# Good: Well-organized module
class ImageClassifier(nn.Module):
def __init__(self, num_classes: int, dropout: float = 0.5) -> None:
super().__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=3, padding=1),
nn.BatchNorm2d(64),
nn.ReLU(inplace=True),
nn.MaxPool2d(2),
)
self.classifier = nn.Sequential(
nn.Dropout(dropout),
nn.Linear(64 * 16 * 16, num_classes),
)
def forward(self, x: torch.Tensor) -> torch.Tensor:
x = self.features(x)
x = x.view(x.size(0), -1)
return self.classifier(x)
# Bad: Everything in forward
class ImageClassifier(nn.Module):
def __init__(self):
super().__init__()
def forward(self, x):
x = F.conv2d(x, weight=self.make_weight()) # Creates weight each call!
return x
Proper Weight Initialization
# Good: Explicit initialization
def _init_weights(self, module: nn.Module) -> None:
if isinstance(module, nn.Linear):
nn.init.kaiming_normal_(module.weight, mode="fan_out", nonlinearity="relu")
if module.bias is not None:
nn.init.zeros_(module.bias)
elif isinstance(module, nn.Conv2d):
nn.init.kaiming_normal_(module.weight, mode="fan_out", nonlinearity="relu")
elif isinstance(module, nn.BatchNorm2d):
nn.init.ones_(module.weight)
nn.init.zeros_(module.bias)
model = MyModel()
model.apply(model._init_weights)
Training Loop Patterns
Standard Training Loop
# Good: Complete training loop with best practices
def train_one_epoch(
model: nn.Module,
dataloader: DataLoader,
optimizer: torch.optim.Optimizer,
criterion: nn.Module,
device: torch.device,
scaler: torch.amp.GradScaler | None = None,
) -> float:
model.train() # Always set train mode
total_loss = 0.0
for batch_idx, (data, target) in enumerate(dataloader):
data, target = data.to(device), target.to(device)
optimizer.zero_grad(set_to_none=True) # More efficient than zero_grad()
# Mixed precision training
with torch.amp.autocast("cuda", enabled=scaler is not None):
output = model(data)
loss = criterion(output, target)
if scaler is not None:
scaler.scale(loss).backward()
scaler.unscale_(optimizer)
torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
scaler.step(optimizer)
scaler.update()
else:
loss.backward()
torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
optimizer.step()
total_loss += loss.item()
return total_loss / len(dataloader)
Validation Loop
# Good: Proper evaluation
@torch.no_grad() # More efficient than wrapping in torch.no_grad() block
def evaluate(
model: nn.Module,
dataloader: DataLoader,
criterion: nn.Module,
device: torch.device,
) -> tuple[float, float]:
model.eval() # Always set eval mode — disables dropout, uses running BN stats
total_loss = 0.0
correct = 0
total = 0
for data, target in dataloader:
data, target = data.to(device), target.to(device)
output = model(data)
total_loss += criterion(output, target).item()
correct += (output.argmax(1) == target).sum().item()
total += target.size(0)
return total_loss / len(dataloader), correct / total
Data Pipeline Patterns
Custom Dataset
# Good: Clean Dataset with type hints
class ImageDataset(Dataset):
def __init__(
self,
image_dir: str,
labels: dict[str, int],
transform: transforms.Compose | None = None,
) -> None:
self.image_paths = list(Path(image_dir).glob("*.jpg"))
self.labels = labels
self.transform = transform
def __len__(self) -> int:
return len(self.image_paths)
def __getitem__(self, idx: int) -> tuple[torch.Tensor, int]:
img = Image.open(self.image_paths[idx]).convert("RGB")
label = self.labels[self.image_paths[idx].stem]
if self.transform:
img = self.transform(img)
return img, label
Efficient DataLoader Configuration
# Good: Optimized DataLoader
dataloader = DataLoader(
dataset,
batch_size=32,
shuffle=True, # Shuffle for training
num_workers=4, # Parallel data loading
pin_memory=True, # Faster CPU->GPU transfer
persistent_workers=True, # Keep workers alive between epochs
drop_last=True, # Consistent batch sizes for BatchNorm
)
# Bad: Slow defaults
dataloader = DataLoader(dataset, batch_size=32) # num_workers=0, no pin_memory
Custom Collate for Variable-Length Data
# Good: Pad sequences in collate_fn
def collate_fn(batch: list[tuple[torch.Tensor, int]]) -> tuple[torch.Tensor, torch.Tensor]:
sequences, labels = zip(*batch)
# Pad to max length in batch
padded = nn.utils.rnn.pad_sequence(sequences, batch_first=True, padding_value=0)
return padded, torch.tensor(labels)
dataloader = DataLoader(dataset, batch_size=32, collate_fn=collate_fn)
Checkpointing Patterns
Save and Load Checkpoints
# Good: Complete checkpoint with all training state
def save_checkpoint(
model: nn.Module,
optimizer: torch.optim.Optimizer,
epoch: int,
loss: float,
path: str,
) -> None:
torch.save({
"epoch": epoch,
"model_state_dict": model.state_dict(),
"optimizer_state_dict": optimizer.state_dict(),
"loss": loss,
}, path)
def load_checkpoint(
path: str,
model: nn.Module,
optimizer: torch.optim.Optimizer | None = None,
) -> dict:
checkpoint = torch.load(path, map_location="cpu", weights_only=True)
model.load_state_dict(checkpoint["model_state_dict"])
if optimizer:
optimizer.load_state_dict(checkpoint["optimizer_state_dict"])
return checkpoint
# Bad: Only saving model weights (can't resume training)
torch.save(model.state_dict(), "model.pt")
Performance Optimization
Mixed Precision Training
# Good: AMP with GradScaler
scaler = torch.amp.GradScaler("cuda")
for data, target in dataloader:
with torch.amp.autocast("cuda"):
output = model(data)
loss = criterion(output, target)
scaler.scale(loss).backward()
scaler.step(optimizer)
scaler.update()
optimizer.zero_grad(set_to_none=True)
Gradient Checkpointing for Large Models
# Good: Trade compute for memory
from torch.utils.checkpoint import checkpoint
class LargeModel(nn.Module):
def forward(self, x: torch.Tensor) -> torch.Tensor:
# Recompute activations during backward to save memory
x = checkpoint(self.block1, x, use_reentrant=False)
x = checkpoint(self.block2, x, use_reentrant=False)
return self.head(x)
torch.compile for Speed
# Good: Compile the model for faster execution (PyTorch 2.0+)
model = MyModel().to(device)
model = torch.compile(model, mode="reduce-overhead")
# Modes: "default" (safe), "reduce-overhead" (faster), "max-autotune" (fastest)
Quick Reference: PyTorch Idioms
| Idiom | Description |
|---|---|
model.train() / model.eval() |
Always set mode before train/eval |
torch.no_grad() |
Disable gradients for inference |
optimizer.zero_grad(set_to_none=True) |
More efficient gradient clearing |
.to(device) |
Device-agnostic tensor/model placement |
torch.amp.autocast |
Mixed precision for 2x speed |
pin_memory=True |
Faster CPU→GPU data transfer |
torch.compile |
JIT compilation for speed (2.0+) |
weights_only=True |
Secure model loading |
torch.manual_seed |
Reproducible experiments |
gradient_checkpointing |
Trade compute for memory |
Anti-Patterns to Avoid
# Bad: Forgetting model.eval() during validation
model.train()
with torch.no_grad():
output = model(val_data) # Dropout still active! BatchNorm uses batch stats!
# Good: Always set eval mode
model.eval()
with torch.no_grad():
output = model(val_data)
# Bad: In-place operations breaking autograd
x = F.relu(x, inplace=True) # Can break gradient computation
x += residual # In-place add breaks autograd graph
# Good: Out-of-place operations
x = F.relu(x)
x = x + residual
# Bad: Moving data to GPU inside the training loop repeatedly
for data, target in dataloader:
model = model.cuda() # Moves model EVERY iteration!
# Good: Move model once before the loop
model = model.to(device)
for data, target in dataloader:
data, target = data.to(device), target.to(device)
# Bad: Using .item() before backward
loss = criterion(output, target).item() # Detaches from graph!
loss.backward() # Error: can't backprop through .item()
# Good: Call .item() only for logging
loss = criterion(output, target)
loss.backward()
print(f"Loss: {loss.item():.4f}") # .item() after backward is fine
# Bad: Not using torch.save properly
torch.save(model, "model.pt") # Saves entire model (fragile, not portable)
# Good: Save state_dict
torch.save(model.state_dict(), "model.pt")
Remember: PyTorch code should be device-agnostic, reproducible, and memory-conscious. When in doubt, profile with torch.profiler and check GPU memory with torch.cuda.memory_summary().
04 同仓库更多 Skills
system-lifecycle-designer
Universal architectural methodology for designing granular, atomic, and sub-atomic lifecycles and end-to-end workflows for single functionality integrations across any domain (daemons, batch jobs, request transactions, resource pools). Provides patterns for deterministic identity, pre-commit validation, differential reconciliation, sticky leasing, state machines, transactional persistence, and closed-loop feedback.
style-sampling
Make a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for "an episode of", "in the style of", "sample this style", 「用这个风格做一集」. One video to copy is reverse-any-video.
reverse-any-video
Rebuild any video file as an editable HyperFrames project - motion graphics, talking heads, live action or AI-generated footage - checked against the original frame by frame. Use to reverse, recreate, remake, replicate or copy a video, or 「复刻这个视频」「照着这个视频做一个」.
typescript-patterns
TypeScript patterns for strict, type-safe, maintainable code in modern TypeScript and JavaScript applications. Covers strict compiler configuration, type design, narrowing, discriminated unions, generics, async and error handling, module boundaries, dependency hygiene, and type-level testing. Use when writing or reviewing TypeScript or JavaScript code.
test-collaboration
Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit/integration/contract/E2E/smoke classification, bug-to-test regression protection, consumer/provider contract testing, test-necessity review, and pre-delivery evidence review.
story-lifecycle
Manage a file-based epic → story → sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira/Linear/Taiga but needs structured delivery tracking.