2.
write a program to demonstrate the working of
Deep Neural Network for Classification in PyTorch
import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import numpy as np
# 1. Load and preprocess the dataset
iris = load_iris()
X = iris.data # Features: sepal length, sepal width, petal length, petal width
y = iris.target # Classes: 0, 1, 2
# Scale features for better training
scaler = StandardScaler()
X = scaler.fit_transform(X)
# Convert to tensors
X = torch.tensor(X, dtype=torch.float32)
y = torch.tensor(y, dtype=torch.long)
# Split into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42)
# 2. Define the deep neural network model
class DeepNN(nn.Module):
def __init__(self, input_size, hidden1, hidden2, output_size):
super(DeepNN, self).__init__()
self.fc1 = nn.Linear(input_size, hidden1) # First hidden layer
self.relu1 = nn.ReLU()
self.fc2 = nn.Linear(hidden1, hidden2) # Second hidden layer
self.relu2 = nn.ReLU()
self.fc3 = nn.Linear(hidden2, output_size) # Output layer
def forward(self, x):
out = self.fc1(x)
out = self.relu1(out)
out = self.fc2(out)
out = self.relu2(out)
out = self.fc3(out)
return out
# 3. Initialize model, loss function, and optimizer
model = DeepNN(input_size=4, hidden1=16, hidden2=8, output_size=3)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.01)
# 4. Training loop
epochs = 100
for epoch in range(epochs):
model.train()
# Forward pass
outputs = model(X_train)
loss = criterion(outputs, y_train)
# Backward pass and optimization
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (epoch+1) % 10 == 0:
print(f"Epoch [{epoch+1}/{epochs}], Loss: {loss.item():.4f}")
# 5. Evaluation
model.eval()
with torch.no_grad():
test_outputs = model(X_test)
_, predicted = torch.max(test_outputs, 1)
accuracy = (predicted == y_test).sum().item() / y_test.size(0)
print(f"\nTest Accuracy: {accuracy*100:.2f}%")
# 6. Show some predictions
print("\nSample Predictions:")
for i in range(5):
print(f"Features: {X_test[i].numpy()}, Predicted: {predicted[i].item()}, Actual:
{y_test[i].item()}")
