CustomDatasetBuilder.py

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.transforms as transforms
import torchvision
import os
import pandas as pd
from skimage import io
from torch.utils.data import (
    Dataset,
    DataLoader,
)

class CatsAndDogsDataset(Dataset):
    def __init__(self, csv_file, root_dir, transform=None):
        self.annotations = pd.read_csv(csv_file)
        self.root_dir = root_dir
        self.transform = transform

    def __len__(self):
        return len(self.annotations)

    def __getitem__(self, index):
        img_path = os.path.join(self.root_dir, self.annotations.iloc[index, 0])
        image = io.imread(img_path)
        y_label = torch.tensor(int(self.annotations.iloc[index, 1]))

        if self.transform:
            image = self.transform(image)

        return (image, y_label)


device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

in_channel = 3
num_classes = 2
learning_rate = 1e-3
batch_size = 32
num_epochs = 10

dataset = CatsAndDogsDataset(
    csv_file="cats_dogs.csv",
    root_dir="cats_dogs_resized",
    transform=transforms.ToTensor(),
)

train_set, test_set = torch.utils.data.random_split(dataset, [5, 5])
train_loader = DataLoader(dataset=train_set, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(dataset=test_set, batch_size=batch_size, shuffle=True)

model = torchvision.models.resnet18(pretrained=True)
model.to(device)

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

for epoch in range(num_epochs):
    losses = []

    for batch_idx, (data, targets) in enumerate(train_loader):
        data = data.to(device=device)
        targets = targets.to(device=device)

        scores = model(data)
        loss = criterion(scores, targets)

        losses.append(loss.item())

        optimizer.zero_grad()
        loss.backward()

        optimizer.step()

    print(f"Cost at epoch {epoch} is {sum(losses)/len(losses)}")

def check_accuracy(loader, model):
    num_correct = 0
    num_samples = 0
    model.eval()

    with torch.no_grad():
        for x, y in loader:
            x = x.to(device=device)
            y = y.to(device=device)

            scores = model(x)
            _, predictions = scores.max(1)
            num_correct += (predictions == y).sum()
            num_samples += predictions.size(0)

        print(f"Got {num_correct} / {num_samples} with accuracy {float(num_correct)/float(num_samples)*100:.2f}")

    model.train()


print("Checking accuracy on Training Set")
check_accuracy(train_loader, model)

print("Checking accuracy on Test Set")
check_accuracy(test_loader, model)