deep-learning（深度学习）

Deep Learning

Build neural networks for computer vision, NLP, and complex data patterns.

Quick Start with PyTorch

import torch
import torch.nn as nn
import torch.optim as optim

# Define model
class NeuralNet(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(NeuralNet, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size)
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(hidden_size, num_classes)

    def forward(self, x):
        out = self.fc1(x)
        out = self.relu(out)
        out = self.fc2(out)
        return out

# Initialize
model = NeuralNet(input_size=784, hidden_size=128, num_classes=10)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# Training loop
for epoch in range(10):
    for images, labels in train_loader:
        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

CNN for Image Classification

class CNN(nn.Module):
    def __init__(self, num_classes=10):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(64 * 8 * 8, 512)
        self.fc2 = nn.Linear(512, num_classes)
        self.dropout = nn.Dropout(0.5)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 64 * 8 * 8)
        x = F.relu(self.fc1(x))
        x = self.dropout(x)
        x = self.fc2(x)
        return x

Transfer Learning

import torchvision.models as models

# Load pre-trained ResNet
model = models.resnet50(pretrained=True)

# Freeze layers
for param in model.parameters():
    param.requires_grad = False

# Replace final layer
num_features = model.fc.in_features
model.fc = nn.Linear(num_features, num_classes)

# Only train final layer
optimizer = optim.Adam(model.fc.parameters(), lr=0.001)

LSTM for Sequences

class LSTMModel(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, output_size):
        super(LSTMModel, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers,
                           batch_first=True, dropout=0.2)
        self.fc = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size)
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size)

        out, _ = self.lstm(x, (h0, c0))
        out = self.fc(out[:, -1, :])
        return out

Transformers with Hugging Face

from transformers import AutoModelForSequenceClassification, Trainer, TrainingArguments

model = AutoModelForSequenceClassification.from_pretrained(
    'bert-base-uncased',
    num_labels=2
)

training_args = TrainingArguments(
    output_dir='./results',
    num_train_epochs=3,
    per_device_train_batch_size=16,
    warmup_steps=500,
    weight_decay=0.01,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset
)

trainer.train()

Tips & Tricks

Regularization:

• Dropout: nn.Dropout(0.5)
• Batch Normalization: nn.BatchNorm2d(channels)
• Weight Decay: optimizer = optim.Adam(params, weight_decay=0.01)
• Early Stopping: Monitor validation loss

Optimization:

• Learning Rate Scheduling: scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=30, gamma=0.1)
• Gradient Clipping: torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)

Data Augmentation:

from torchvision import transforms

transform = transforms.Compose([
    transforms.RandomHorizontalFlip(),
    transforms.RandomRotation(10),
    transforms.ColorJitter(brightness=0.2, contrast=0.2),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406],
                        std=[0.229, 0.224, 0.225])
])

Common Issues

Overfitting:

• Add dropout
• Data augmentation
• Early stopping
• Reduce model complexity

Underfitting:

• Increase model capacity
• Train longer
• Reduce regularization
• Better features

Vanishing Gradients:

• Use ReLU activation
• Batch normalization
• Residual connections
• Proper initialization