### 3. Training Loop

criterion = nn.BCELoss()          # Binary Cross Entropy
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

for epoch in range(1000):
    # Forward pass
    outputs = model(X)
    loss = criterion(outputs, y)
    
    # Backward pass
    optimizer.zero_grad()  # Clear old gradients
    loss.backward()        # Compute gradients
    optimizer.step()       # Update weights
    
    if (epoch+1) % 100 == 0:
        print(f'Epoch {epoch+1}, Loss: {loss.item():.4f}')

# Test
with torch.no_grad():
    predictions = model(X).round()
    print(f"Final predictions: {predictions.squeeze()}")

---

## 🔹 Best Practices for Beginners
1. Always clear gradients with optimizer.zero_grad() before backward()
2. Use `with torch.no_grad():` for inference (disables gradient tracking)
3. Normalize input data (e.g., scale to [0, 1] or standardize)
4. Start simple before using complex architectures
5. Leverage GPU for larger models/datasets

---

### 📌 What's Next?
In Part 2, we'll cover:
➡️ Deep Neural Networks (DNNs)
➡️ Activation Functions
➡️ Batch Normalization
➡️ Handling Real Datasets

#PyTorch #DeepLearning #MachineLearning 🚀

Practice Exercise:
1. Create a tensor of shape (3, 4) with random values (0-1)
2. Compute the mean of each column
3. Build a perceptron for OR gate (modify the XOR example)
4. Plot the loss curve during training

# Solution for exercise 1-2
x = torch.rand(3, 4)
col_means = x.mean(dim=0)  # dim=0 → average along rows

# 📚 PyTorch Tutorial for Beginners - Part 2/6: Deep Neural Networks & Training Techniques
#PyTorch #DeepLearning #MachineLearning #NeuralNetworks #Training

Welcome to Part 2 of our comprehensive PyTorch series! This lesson dives deep into building and training neural networks, covering architectures, activation functions, optimization, and more.

---

## 🔹 Recap & Setup

import torch
import torch.nn as nn
import torch.optim as optim
import matplotlib.pyplot as plt
from torch.utils.data import DataLoader, TensorDataset

# Check GPU
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(f"Using device: {device}")

---

## 🔹 Deep Neural Network (DNN) Architecture
### 1. Key Components
| Component | Purpose | PyTorch Implementation |
|--------------------|-------------------------------------------------------------------------|------------------------------|
| Input Layer | Receives raw features | nn.Linear(input_dim, hidden_dim) |
| Hidden Layers | Learn hierarchical representations | Multiple nn.Linear + Activation |
| Output Layer | Produces final predictions | nn.Linear(hidden_dim, output_dim) |
| Activation | Introduces non-linearity | nn.ReLU(), nn.Sigmoid(), etc. |
| Loss Function | Measures prediction error | nn.MSELoss(), nn.CrossEntropyLoss() |
| Optimizer | Updates weights to minimize loss | optim.SGD(), optim.Adam() |

### 2. Building a DNN

class DNN(nn.Module):
    def __init__(self, input_size, hidden_sizes, output_size):
        super().__init__()
        layers = []
        
        # Hidden layers
        prev_size = input_size
        for hidden_size in hidden_sizes:
            layers.append(nn.Linear(prev_size, hidden_size))
            layers.append(nn.ReLU())
            prev_size = hidden_size
            
        # Output layer (no activation for regression)
        layers.append(nn.Linear(prev_size, output_size))
        
        self.net = nn.Sequential(*layers)
        
    def forward(self, x):
        return self.net(x)

# Example: 3-layer network (input=10, hidden=[64,32], output=1)
model = DNN(10, [64, 32], 1).to(device)
print(model)

---

## 🔹 Activation Functions
### 1. Common Choices
| Activation | Formula | Range | Use Case | PyTorch |
|-----------------|----------------------|------------|------------------------------|------------------|
| ReLU | max(0, x) | [0, ∞) | Hidden layers | nn.ReLU() |
| Leaky ReLU | max(0.01x, x) | (-∞, ∞) | Avoid dead neurons | nn.LeakyReLU() |
| Sigmoid | 1 / (1 + e^(-x)) | (0, 1) | Binary classification | nn.Sigmoid() |
| Tanh | (e^x - e^(-x)) / ... | (-1, 1) | RNNs, some hidden layers | nn.Tanh() |
| Softmax | e^x / sum(e^x) | (0, 1) | Multi-class classification | nn.Softmax() |

### 2. Visual Comparison

x = torch.linspace(-5, 5, 100)
activations = {
    "ReLU": nn.ReLU()(x),
    "LeakyReLU": nn.LeakyReLU(0.1)(x),
    "Sigmoid": nn.Sigmoid()(x),
    "Tanh": nn.Tanh()(x)
}

plt.figure(figsize=(12, 4))
for i, (name, y) in enumerate(activations.items()):
    plt.subplot(1, 4, i+1)
    plt.plot(x.numpy(), y.numpy())
    plt.title(name)
plt.tight_layout()
plt.show()

---

## 🔹 Complete Training Pipeline
### 1. Training Loop

def train(model, train_loader, criterion, optimizer, epochs=10):
    model.train()
    losses = []
    
    for epoch in range(epochs):
        running_loss = 0.0
        
        for inputs, labels in train_loader:
            inputs, labels = inputs.to(device), labels.to(device)
            
            # Forward pass
            outputs = model(inputs)
            loss = criterion(outputs, labels)
            
            # Backward pass
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            
            running_loss += loss.item()
        
        epoch_loss = running_loss / len(train_loader)
        losses.append(epoch_loss)
        print(f'Epoch {epoch+1}/{epochs}, Loss: {epoch_loss:.4f}')
    
    return losses

### 2. Evaluation Function

def evaluate(model, test_loader):
    model.eval()
    correct = 0
    total = 0
    
    with torch.no_grad():
        for inputs, labels in test_loader:
            inputs, labels = inputs.to(device), labels.to(device)
            outputs = model(inputs)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    
    accuracy = 100 * correct / total
    print(f'Test Accuracy: {accuracy:.2f}%')
    return accuracy

### 3. Full Execution

# Hyperparameters
input_size = 784  # MNIST images (28x28)
hidden_sizes = [128, 64]
output_size = 10   # Digits 0-9
lr = 0.001
epochs = 10

# Initialize
model = DNN(input_size, hidden_sizes, output_size).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=lr)

# Flatten MNIST images
train_loader.dataset.transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,)),
    transforms.Lambda(lambda x: x.view(-1))  # Flatten
])

# Train and evaluate
losses = train(model, train_loader, criterion, optimizer, epochs)
evaluate(model, test_loader)

# Plot training curve
plt.plot(losses)
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.title('Training Loss Curve')
plt.show()

---

## 🔹 Debugging & Visualization
### 1. Gradient Checking

# After loss.backward()
for name, param in model.named_parameters():
    if param.grad is not None:
        print(f"{name} gradient mean: {param.grad.mean().item():.6f}")

### 2. Weight Histograms

def plot_weights(model):
    for name, param in model.named_parameters():
        if 'weight' in name:
            plt.figure()
            plt.hist(param.detach().cpu().numpy().flatten(), bins=50)
            plt.title(name)
            plt.show()

---

## 🔹 Advanced Techniques
### 1. Weight Initialization

def init_weights(m):
    if isinstance(m, nn.Linear):
        nn.init.xavier_uniform_(m.weight)
        nn.init.zeros_(m.bias)

model.apply(init_weights)

### 2. Early Stopping

best_loss = float('inf')
patience = 3
trigger_times = 0

for epoch in range(100):
    # Training...
    val_loss = validate(model, val_loader, criterion)
    
    if val_loss < best_loss:
        best_loss = val_loss
        trigger_times = 0
        torch.save(model.state_dict(), 'best_model.pth')
    else:
        trigger_times += 1
        if trigger_times >= patience:
            print("Early stopping!")
            break

---

## 🔹 Best Practices
1. Always normalize input data (e.g., scale to [0,1] or standardize)
2. Use batch normalization for deeper networks
3. Start with Adam optimizer (lr=0.001) as default
4. Monitor training with validation set to detect overfitting
5. Visualize weight distributions periodically
6. Use GPU for training (model.to(device))

---

### 📌 What's Next?
In Part 3, we'll cover:
➡️ Convolutional Neural Networks (CNNs)
➡️ Transfer Learning
➡️ Image Augmentation Techniques
➡️ Visualizing CNNs

#PyTorch #DeepLearning #MachineLearning 🚀

# 📚 PyTorch Tutorial for Beginners - Part 3/6: Convolutional Neural Networks (CNNs) & Computer Vision
#PyTorch #DeepLearning #ComputerVision #CNNs #TransferLearning

Welcome to Part 3 of our PyTorch series! This comprehensive lesson dives deep into Convolutional Neural Networks (CNNs), the powerhouse behind modern computer vision applications. We'll cover architecture design, implementation tricks, transfer learning, and visualization techniques.

---

## 🔹 Introduction to CNNs
### Why CNNs for Images?
Traditional fully-connected networks (DNNs) fail for images because:
- Parameter explosion: A 256x256 RGB image → 196,608 input features
- No spatial awareness: DNNs treat pixels as independent features
- Translation variance: Objects in different positions require re-learning

### CNN Key Innovations
| Concept | Purpose | Visual Example |
|--------------------|-------------------------------------------------------------------------|-----------------------------|
| Local Receptive Fields | Processes small regions at a time (e.g., 3x3 windows) |  |
| Weight Sharing | Same filters applied across entire image (reduces parameters) | |
| Hierarchical Features | Early layers detect edges → textures → object parts → whole objects |  |

---

## 🔹 Core CNN Components
### 1. Convolutional Layers

import torch.nn as nn

# 2D convolution (for images)
conv = nn.Conv2d(
    in_channels=3,    # Input channels (RGB=3, grayscale=1)
    out_channels=16,  # Number of filters
    kernel_size=3,    # 3x3 filter
    stride=1,         # Filter movement step
    padding=1         # Preserves spatial dimensions (with stride=1)
)

# Shape transformation: (batch, channels, height, width)
x = torch.randn(32, 3, 64, 64)  # 32 RGB images of 64x64
print(conv(x).shape)  # → torch.Size([32, 16, 64, 64])

### 2. Pooling Layers

# Max pooling (common for downsampling)
pool = nn.MaxPool2d(kernel_size=2, stride=2)
print(pool(conv(x)).shape)  # → torch.Size([32, 16, 32, 32])

# Adaptive pooling (useful for varying input sizes)
adaptive_pool = nn.AdaptiveAvgPool2d((7, 7))
print(adaptive_pool(x).shape)  # → torch.Size([32, 3, 7, 7])

### 3. Normalization Layers

# Batch Normalization
bn = nn.BatchNorm2d(16)  # num_features = out_channels
x = conv(x)
x = bn(x)

# Layer Normalization (for NLP/sequences)
ln = nn.LayerNorm([16, 64, 64])

### 4. Dropout

# Spatial dropout (drops entire channels)
dropout = nn.Dropout2d(p=0.25)

---

## 🔹 Building a CNN from Scratch
### Complete Architecture

class CNN(nn.Module):
    def __init__(self, num_classes=10):
        super().__init__()
        self.features = nn.Sequential(
            # Block 1
            nn.Conv2d(3, 32, kernel_size=3, padding=1),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(2),
            
            # Block 2
            nn.Conv2d(32, 64, kernel_size=3, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(2),
            
            # Block 3
            nn.Conv2d(64, 128, kernel_size=3, padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.MaxPool2d(2),
        )
        
        self.classifier = nn.Sequential(
            nn.Linear(128 * 4 * 4, 512),  # Adjusted based on input size
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(512, num_classes)
        )
        
    def forward(self, x):
        x = self.features(x)
        x = torch.flatten(x, 1)  # Flatten all dimensions except batch
        x = self.classifier(x)
        return x

# Usage
model = CNN().to(device)
print(model)

### Shape Calculation Formula
For a layer with:
- Input size: (Hᵢₙ, Wᵢₙ)
- Kernel: K
- Padding: P
- Stride: S

Output dimensions:

Hₒᵤₜ = ⌊(Hᵢₙ + 2P - K)/S⌋ + 1
Wₒᵤₜ = ⌊(Wᵢₙ + 2P - K)/S⌋ + 1

---

# 📚 PyTorch Tutorial for Beginners - Part 4/6: Sequence Modeling with RNNs, LSTMs & Attention
#PyTorch #DeepLearning #NLP #RNN #LSTM #Transformer

Welcome to Part 4 of our PyTorch series! This comprehensive lesson dives deep into sequence modeling, covering recurrent networks, attention mechanisms, and transformer architectures with practical implementations.

---

## 🔹 Introduction to Sequence Modeling
### Key Challenges with Sequences
1. Variable Length: Sequences can be arbitrarily long (sentences, time series)
2. Temporal Dependencies: Current output depends on previous inputs
3. Context Preservation: Need to maintain long-range relationships

### Comparison of Approaches
| Model Type | Pros | Cons | Typical Use Cases |
|------------------|---------------------------------------|---------------------------------------|---------------------------------|
| RNN | Simple, handles sequences | Struggles with long-term dependencies | Short time series, char-level NLP |
| LSTM | Better long-term memory | Computationally heavier | Machine translation, speech recognition |
| GRU | LSTM-like with fewer parameters | Still limited context | Medium-length sequences |
| Transformer | Parallel processing, global context | Memory intensive for long sequences | Modern NLP, any sequence task |

---

## 🔹 Recurrent Neural Networks (RNNs)
### 1. Basic RNN Architecture

class VanillaRNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super().__init__()
        self.hidden_size = hidden_size
        self.rnn = nn.RNN(input_size, hidden_size, batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)
        
    def forward(self, x, hidden=None):
        # x shape: (batch, seq_len, input_size)
        out, hidden = self.rnn(x, hidden)
        # Only use last output for classification
        out = self.fc(out[:, -1, :])  
        return out

# Usage
rnn = VanillaRNN(input_size=10, hidden_size=20, output_size=5)
x = torch.randn(3, 15, 10)  # (batch=3, seq_len=15, input_size=10)
output = rnn(x)

### 2. The Vanishing Gradient Problem
RNNs struggle with long sequences due to:
- Repeated multiplication of small gradients through time
- Exponential decay of gradient information

Solutions:
- Gradient clipping
- Architectural changes (LSTM, GRU)
- Skip connections

---

## 🔹 Long Short-Term Memory (LSTM) Networks
### 1. LSTM Core Concepts

Key Components:
- Forget Gate: Decides what information to discard
- Input Gate: Updates cell state with new information
- Output Gate: Determines next hidden state

### 2. PyTorch Implementation

class LSTMModel(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, output_size):
        super().__init__()
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, 
                           batch_first=True, dropout=0.2 if num_layers>1 else 0)
        self.fc = nn.Linear(hidden_size, output_size)
        
    def forward(self, x):
        # Initialize hidden state and cell state
        h0 = torch.zeros(self.lstm.num_layers, x.size(0), 
                        self.lstm.hidden_size).to(x.device)
        c0 = torch.zeros_like(h0)
        
        out, (hn, cn) = self.lstm(x, (h0, c0))
        out = self.fc(out[:, -1, :])
        return out

# Bidirectional LSTM example
bidir_lstm = nn.LSTM(input_size=10, hidden_size=20, num_layers=2,
                    bidirectional=True, batch_first=True)

# Learning rate scheduler for transformers
def lr_schedule(step, d_model=512, warmup_steps=4000):
    arg1 = step ** -0.5
    arg2 = step * (warmup_steps ** -1.5)
    return (d_model ** -0.5) * min(step ** -0.5, step * warmup_steps ** -1.5)

---

### **📌 What's Next?
In **Part 5, we'll cover:
➡️ Generative Models (GANs, VAEs)
➡️ Reinforcement Learning with PyTorch
➡️ Model Optimization & Deployment
➡️ PyTorch Lightning Best Practices

#PyTorch #DeepLearning #NLP #Transformers 🚀

Practice Exercises:
1. Implement a character-level language model with LSTM
2. Add attention visualization to a sentiment analysis model
3. Build a transformer from scratch for machine translation
4. Compare teacher forcing ratios in seq2seq training
5. Implement beam search for decoder inference

# Character-level LSTM starter
class CharLSTM(nn.Module):
    def __init__(self, vocab_size, hidden_size, n_layers):
        super().__init__()
        self.embed = nn.Embedding(vocab_size, hidden_size)
        self.lstm = nn.LSTM(hidden_size, hidden_size, n_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, vocab_size)
        
    def forward(self, x, hidden=None):
        x = self.embed(x)
        out, hidden = self.lstm(x, hidden)
        return self.fc(out), hidden

# 📚 PyTorch Tutorial for Beginners - Part 5/6: Generative Models & Advanced Topics
#PyTorch #DeepLearning #GANs #VAEs #ReinforcementLearning #Deployment

Welcome to Part 5 of our PyTorch series! This comprehensive lesson explores generative modeling, reinforcement learning, model optimization, and deployment strategies with practical implementations.

---

## 🔹 Generative Adversarial Networks (GANs)
### 1. GAN Core Concepts

Key Components:
- Generator: Creates fake samples from noise (typically a transposed CNN)
- Discriminator: Distinguishes real vs. fake samples (CNN classifier)
- Adversarial Training: The two networks compete in a minimax game

### 2. DCGAN Implementation

class Generator(nn.Module):
    def __init__(self, latent_dim, img_channels, features_g):
        super().__init__()
        self.net = nn.Sequential(
            # Input: N x latent_dim x 1 x 1
            nn.ConvTranspose2d(latent_dim, features_g*8, 4, 1, 0, bias=False),
            nn.BatchNorm2d(features_g*8),
            nn.ReLU(),
            # 4x4
            nn.ConvTranspose2d(features_g*8, features_g*4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(features_g*4),
            nn.ReLU(),
            # 8x8
            nn.ConvTranspose2d(features_g*4, features_g*2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(features_g*2),
            nn.ReLU(),
            # 16x16
            nn.ConvTranspose2d(features_g*2, img_channels, 4, 2, 1, bias=False),
            nn.Tanh()
            # 32x32
        )

    def forward(self, x):
        return self.net(x)

class Discriminator(nn.Module):
    def __init__(self, img_channels, features_d):
        super().__init__()
        self.net = nn.Sequential(
            # Input: N x img_channels x 32 x 32
            nn.Conv2d(img_channels, features_d, 4, 2, 1, bias=False),
            nn.LeakyReLU(0.2),
            # 16x16
            nn.Conv2d(features_d, features_d*2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(features_d*2),
            nn.LeakyReLU(0.2),
            # 8x8
            nn.Conv2d(features_d*2, features_d*4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(features_d*4),
            nn.LeakyReLU(0.2),
            # 4x4
            nn.Conv2d(features_d*4, 1, 4, 1, 0, bias=False),
            nn.Sigmoid()
        )

    def forward(self, x):
        return self.net(x)

# Initialize
gen = Generator(latent_dim=100, img_channels=3, features_g=64).to(device)
disc = Discriminator(img_channels=3, features_d=64).to(device)

# Loss and optimizers
criterion = nn.BCELoss()
opt_gen = optim.Adam(gen.parameters(), lr=0.0002, betas=(0.5, 0.999))
opt_disc = optim.Adam(disc.parameters(), lr=0.0002, betas=(0.5, 0.999))

### 3. GAN Training Loop

def train_gan(gen, disc, loader, num_epochs):
    fixed_noise = torch.randn(32, 100, 1, 1).to(device)
    
    for epoch in range(num_epochs):
        for batch_idx, (real, _) in enumerate(loader):
            real = real.to(device)
            noise = torch.randn(real.size(0), 100, 1, 1).to(device)
            fake = gen(noise)
            
            # Train Discriminator
            disc_real = disc(real).view(-1)
            loss_disc_real = criterion(disc_real, torch.ones_like(disc_real))
            disc_fake = disc(fake.detach()).view(-1)
            loss_disc_fake = criterion(disc_fake, torch.zeros_like(disc_fake))
            loss_disc = (loss_disc_real + loss_disc_fake) / 2
            disc.zero_grad()
            loss_disc.backward()
            opt_disc.step()
            
            # Train Generator
            output = disc(fake).view(-1)
            loss_gen = criterion(output, torch.ones_like(output))
            gen.zero_grad()
            loss_gen.backward()
            opt_gen.step()
            
        # Visualization
        with torch.no_grad():
            fake = gen(fixed_noise)
            save_image(fake, f"gan_samples/epoch_{epoch}.png", normalize=True)

### 2. Pruning

parameters_to_prune = (
    (model.conv1, 'weight'),
    (model.fc1, 'weight'),
)

prune.global_unstructured(
    parameters_to_prune,
    pruning_method=prune.L1Unstructured,
    amount=0.2
)

# Remove pruning reparameterization
for module, param in parameters_to_prune:
    prune.remove(module, param)

### 3. ONNX Export

dummy_input = torch.randn(1, 3, 224, 224)
torch.onnx.export(
    model,
    dummy_input,
    "model.onnx",
    input_names=["input"],
    output_names=["output"],
    dynamic_axes={
        "input": {0: "batch_size"},
        "output": {0: "batch_size"}
    }
)

### 4. TorchScript

# Tracing
example_input = torch.rand(1, 3, 224, 224)
traced_script = torch.jit.trace(model, example_input)
traced_script.save("traced_model.pt")

# Scripting
scripted_model = torch.jit.script(model)
scripted_model.save("scripted_model.pt")

---

## 🔹 PyTorch Lightning Best Practices
### 1. LightningModule Structure

import pytorch_lightning as pl

class LitModel(pl.LightningModule):
    def __init__(self, learning_rate=1e-3):
        super().__init__()
        self.save_hyperparameters()
        self.model = nn.Sequential(
            nn.Linear(28*28, 128),
            nn.ReLU(),
            nn.Linear(128, 10)
        )
    
    def forward(self, x):
        return self.model(x)
    
    def training_step(self, batch, batch_idx):
        x, y = batch
        y_hat = self(x)
        loss = nn.functional.cross_entropy(y_hat, y)
        self.log('train_loss', loss)
        return loss
    
    def validation_step(self, batch, batch_idx):
        x, y = batch
        y_hat = self(x)
        loss = nn.functional.cross_entropy(y_hat, y)
        self.log('val_loss', loss)
    
    def configure_optimizers(self):
        return optim.Adam(self.parameters(), lr=self.hparams.learning_rate)

# Training
trainer = pl.Trainer(gpus=1, max_epochs=10)
model = LitModel()
trainer.fit(model, train_loader, val_loader)

### 2. Advanced Lightning Features

# Mixed Precision
trainer = pl.Trainer(precision=16)

# Distributed Training
trainer = pl.Trainer(gpus=2, accelerator='ddp')

# Callbacks
early_stop = pl.callbacks.EarlyStopping(monitor='val_loss')
checkpoint = pl.callbacks.ModelCheckpoint(monitor='val_loss')
trainer = pl.Trainer(callbacks=[early_stop, checkpoint])

# Logging
trainer = pl.Trainer(logger=pl.loggers.TensorBoardLogger('logs/'))

---

## 🔹 Best Practices Summary
1. For GANs: Use spectral norm, progressive growing, and TTUR
2. For VAEs: Monitor both reconstruction and KL divergence terms
3. For RL: Properly normalize rewards and use experience replay
4. For Deployment: Quantize, prune, and export to optimized formats
5. For Maintenance: Use PyTorch Lightning for reproducible experiments

---

### 📌 What's Next?
In Part 6 (Final), we'll cover:
➡️ Advanced Architectures (Graph NNs, Neural ODEs)
➡️ Model Interpretation Techniques
➡️ Production Deployment (TorchServe, Flask API)
➡️ PyTorch Ecosystem (TorchVision, TorchText, TorchAudio)

#PyTorch #DeepLearning #GANs #ReinforcementLearning 🚀

Practice Exercises:
1. Implement WGAN-GP with gradient penalty
2. Train a VAE on MNIST and visualize latent space
3. Build a DQN agent for CartPole environment
4. Quantize a pretrained ResNet and compare accuracy/speed
5. Convert a model to TorchScript and serve with Flask

# WGAN-GP Gradient Penalty
def compute_gradient_penalty(D, real_samples, fake_samples):
    alpha = torch.rand(real_samples.size(0), 1, 1, 1).to(device)
    interpolates = (alpha * real_samples + (1 - alpha) * fake_samples).requires_grad_(True)
    d_interpolates = D(interpolates)
    gradients = torch.autograd.grad(
        outputs=d_interpolates,
        inputs=interpolates,
        grad_outputs=torch.ones_like(d_interpolates),
        create_graph=True,
        retain_graph=True,
        only_inputs=True
    )[0]
    gradients = gradients.view(gradients.size(0), -1)
    gradient_penalty = ((gradients.norm(2, dim=1) - 1) ** 2).mean()
    return gradient_penalty