main.py

from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.optim.lr_scheduler import StepLR
from torch.utils.data import Dataset, DataLoader
import pandas as pd


class PersianDigitsDataset(Dataset):

    def __init__(self, csv_file):
        self.persian_digits_frame = pd.read_csv(csv_file)

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

    def __getitem__(self, idx):
        if torch.is_tensor(idx):
            idx = idx.tolist()

        return torch.Tensor(self.persian_digits_frame.iloc[idx][1:]).reshape([1, 28, 28]), self.persian_digits_frame.iloc[idx][0]


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.dropout1 = nn.Dropout2d(0.25)
        self.dropout2 = nn.Dropout2d(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output


def train(args, model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train epoch: {} [{}/{} ({:.0f}%)]\tloss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))


def validation(args, model, device, validation_loader):
    model.eval()
    validation_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in validation_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            validation_loss += F.nll_loss(output, target, reduction='sum').item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    validation_loss /= len(validation_loader.dataset)

    print('\nValidation set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        validation_loss, correct, len(validation_loader.dataset),
        100. * correct / len(validation_loader.dataset)))


def test(args, model, device, test_loader):
    model.eval()
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            pred = output.argmax(dim=1, keepdim=True)  # get the index of the max log-probability

    print("Predicted result:")
    for i in range(len(pred)):
        print(str(i) + "," + str(int(pred[i])))


def main():
    parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
    parser.add_argument('--batch-size', type=int, default=128, metavar='N',
                        help='input batch size for training (default: 128)')
    parser.add_argument('--validation-batch-size', type=int, default=512, metavar='N',
                        help='input batch size for validation (default: 512)')
    parser.add_argument('--test-batch-size', type=int, default=512, metavar='N',
                        help='input batch size for test (default: 512)')
    parser.add_argument('--epochs', type=int, default=20, metavar='N',
                        help='number of epochs to train (default: 20)')
    parser.add_argument('--lr', type=float, default=1.0, metavar='LR',
                        help='learning rate (default: 1.0)')
    parser.add_argument('--gamma', type=float, default=0.7, metavar='M',
                        help='Learning rate step gamma (default: 0.7)')
    parser.add_argument('--no-cuda', action='store_true', default=False,
                        help='disables CUDA training')
    parser.add_argument('--seed', type=int, default=1, metavar='S',
                        help='random seed (default: 1)')
    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                        help='how many batches to wait before logging training status')

    parser.add_argument('--save-model', action='store_true', default=False,
                        help='For Saving the current Model')
    args = parser.parse_args()
    use_cuda = not args.no_cuda and torch.cuda.is_available()

    torch.manual_seed(args.seed)

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

    kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
    train_loader = torch.utils.data.DataLoader(
        PersianDigitsDataset("large_dataset_train.csv"),
        batch_size=args.batch_size, shuffle=True, **kwargs)
    validation_loader = torch.utils.data.DataLoader(
        PersianDigitsDataset("large_dataset_validation.csv"),
        batch_size=args.validation_batch_size, shuffle=True, **kwargs)
    test_loader = torch.utils.data.DataLoader(
        PersianDigitsDataset("large_dataset_test.csv"),
        batch_size=args.test_batch_size, shuffle=False, **kwargs)

    model = Net().to(device)
    optimizer = optim.Adadelta(model.parameters(), lr=args.lr)

    scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
    for epoch in range(1, args.epochs + 1):
        train(args, model, device, train_loader, optimizer, epoch)
        validation(args, model, device, validation_loader)
        scheduler.step()

    test(args, model, device, test_loader)

    if args.save_model:
        torch.save(model.state_dict(), "mnist_cnn.pt")


if __name__ == '__main__':
    main()