linear1 = torch.nn.Linear(784, 32, bias=True)
linear2 = torch.nn.Linear(32, 32, bias=True)
linear3 = torch.nn.Linear(32, 10, bias=True)
relu = torch.nn.ReLU()
bn1 = torch.nn.BatchNorm1d(32)
bn2 = torch.nn.BatchNorm1d(32)

# BatchNorm을 사용하지 않는 모델을 만들기 위한 Linear layer 만들기
nn_linear1 = torch.nn.Linear(784, 32, bias=True)
nn_linear2 = torch.nn.Linear(32, 32, bias=True)
nn_linear3 = torch.nn.Linear(32, 10, bias=True)

# 모델 정의
bn_model = torch.nn.Sequential(linear1, bn1, relu,
                               linear2, bn2, relu,
                               linear3).to(device)
nn_model = torch.nn.Sequential(linear1, relu,
                               linear2, relu,
                               linear3).to(device)

# 학습 & 각epoch 마다 평가
for epoch in range(epochs):
    bn_model.train()
    for X, Y in train_loader:
        X = X.view(-1, 28*28).to(device)
        Y = Y.to(device)
		.
		.
		.
	with torch.no_grad():
		bn_model.eval()

		# train셋을 통한 평가
		bn_loss, nn_loss, bn_Acc, nn_Acc = 0, 0, 0, 0
		for i, (X, Y) in enumerate(train_loader):
			X = X.view(-1, 28 * 28).to(device)
			Y = Y.to(device)
			.
			.
			.
		# test셋을 통한 평가
        bn_loss, nn_loss, bn_Acc, nn_Acc = 0, 0, 0, 0
        for i, (X, Y) in enumerate(test_loader):
            X = X.view(-1, 28 * 28).to(device)
            Y = Y.to(device)
			.
			.
			.