cat_dog_cnn.py

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
from torchvision.utils import make_grid
import matplotlib.pyplot as plt

# Define the CNN architecture for cat and dog classification
class CatDogClassifier(nn.Module):
    def __init__(self):
        super(CatDogClassifier, 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 * 56 * 56, 128)
        self.fc2 = nn.Linear(128, 2)

    def forward(self, x):
        x = self.pool(nn.functional.relu(self.conv1(x)))
        x = self.pool(nn.functional.relu(self.conv2(x)))
        x = x.view(-1, 64 * 56 * 56)
        x = nn.functional.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# Load and preprocess the cat and dog dataset
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

train_dataset = datasets.ImageFolder(root='./data/train', transform=transform)
test_dataset = datasets.ImageFolder(root='./data/test', transform=transform)

train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)

# Initialize the model, loss function, and optimizer
model = CatDogClassifier()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# Train the model
num_epochs = 5
for epoch in range(num_epochs):
    for images, labels in train_loader:
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

# Test the model
correct = 0
total = 0
with torch.no_grad():
    for images, labels in test_loader:
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

accuracy = correct / total
print(f'Test accuracy: {accuracy}')

# Visualize some predictions
dataiter = iter(test_loader)
images, labels = dataiter.next()
outputs = model(images)
_, predicted = torch.max(outputs, 1)

# Function to show images
def imshow(img):
    img = img / 2 + 0.5  # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

# Show images and their predicted labels
imshow(make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % train_dataset.classes[labels[j]] for j in range(4)))
print('Predicted:   ', ' '.join('%5s' % train_dataset.classes[predicted[j]] for j in range(4)))