resnet50_model.py

import os
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms, models
from torch.utils.data import DataLoader

# Paths to your dataset
train_dir = 'data/apple-leaf-disease-dataset/train_data'
test_dir = 'data/apple-leaf-disease-dataset/test_data'

# Define image transformations
transform = transforms.Compose([
    transforms.Resize((256, 256)),  # Resize images to a common size
    transforms.RandomHorizontalFlip(),  # Data augmentation
    transforms.RandomVerticalFlip(),  # Data augmentation
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),  # Normalize with ImageNet stats
])

# Create datasets
train_dataset = datasets.ImageFolder(root=train_dir, transform=transform)
test_dataset = datasets.ImageFolder(root=test_dir, transform=transform)

# Create data loaders
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True, num_workers=4)
test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False, num_workers=4)

# Define the Bottleneck block
class Bottleneck(nn.Module):
    expansion = 4
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.expansion = 4
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.conv3 = nn.Conv2d(out_channels, out_channels * self.expansion, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn3 = nn.BatchNorm2d(out_channels * self.expansion)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x

        if self.downsample is not None:
            identity = self.downsample(x)

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)
        out = self.conv3(out)
        out = self.bn3(out)

        out += identity
        out = self.relu(out)

        return out

# Define the ResNet-50 model
class ResNet50(nn.Module):
    def __init__(self, num_classes):
        super(ResNet50, self).__init__()
        self.in_channels = 64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(Bottleneck, 64, 3)
        self.layer2 = self._make_layer(Bottleneck, 128, 4, stride=2)
        self.layer3 = self._make_layer(Bottleneck, 256, 6, stride=2)
        self.layer4 = self._make_layer(Bottleneck, 512, 3, stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * 4, num_classes)

    def _make_layer(self, block, out_channels, blocks, stride=1):
        downsample = None
        if stride != 1 or self.in_channels != out_channels * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channels, out_channels * block.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_channels * block.expansion),
            )

        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.in_channels, out_channels))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.fc(x)

        return x

# Initialize model
num_classes = len(train_dataset.classes)  # Number of classes in dataset
model = ResNet50(num_classes=num_classes)

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

# Training function
def train_model(model, train_loader, criterion, optimizer, num_epochs=25):
    model.train()
    for epoch in range(num_epochs):
        running_loss = 0.0
        for inputs, labels in train_loader:
            optimizer.zero_grad()
            outputs = model(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
            running_loss += loss.item() * inputs.size(0)
        
        epoch_loss = running_loss / len(train_loader.dataset)
        print(f"Epoch {epoch + 1}/{num_epochs}, Loss: {epoch_loss:.4f}")

    print("Training complete.")

# Evaluation function
def evaluate_model(model, test_loader):
    model.eval()
    correct = 0
    total = 0
    with torch.no_grad():
        for inputs, labels in test_loader:
            outputs = model(inputs)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()

    accuracy = 100 * correct / total
    print(f'Accuracy: {accuracy:.2f}%')

# Train the model
train_model(model, train_loader, criterion, optimizer)

# Evaluate the model
evaluate_model(model, test_loader)

# Save the model
torch.save(model.state_dict(), 'resnet50_apple_leaf_disease.pth')
print("Model saved to 'resnet50_apple_leaf_disease.pth'")