민석이는 손글씨 인식 프로그램 개발을 위해 우선 MNIST 데이터셋을 기계학습시키는 과정을 거치려고 한다. 아직은 실력이 부족해 학습의 정확도가 70%에 불과한데, 파이토치를 잘 아는 우리가 그동안 배운 방법으로 민석이를 도와 정확도를 96%까지 올려보도록 하자. (정확도도 첨부해주세요!)

import torch
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import random

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

# for reproducibility
random.seed(777)
torch.manual_seed(777)
if device == 'cuda':
    torch.cuda.manual_seed_all(777)

# parameters
learning_rate = 0.01
training_epochs = 10
batch_size = 50

# MNIST dataset
mnist_train = dsets.MNIST(root='MNIST_data/',
                          train=True,
                          transform=transforms.ToTensor(),
                          download=True)

mnist_test = dsets.MNIST(root='MNIST_data/',
                         train=False,
                         transform=transforms.ToTensor(),
                         download=True)

# dataset loader
data_loader = torch.utils.data.DataLoader(dataset=mnist_train,
                                          batch_size=batch_size,
                                          shuffle=True,
                                          drop_last=True)
# layer
linear = torch.nn.Linear(784, 10, bias=True).to(device)

# 활성화함수
sigmoid = torch.nn.Sigmoid()

# model
model = torch.nn.Sequential(linear, sigmoid).to(device)

# optimizer
criterion = torch.nn.CrossEntropyLoss().to(device)
optimizer = torch.optim.SGD(linear.parameters(), lr=learning_rate)

total_batch = len(data_loader)
model.eval()   
for epoch in range(training_epochs):
    avg_cost = 0

    for X, Y in data_loader:
        # reshape input image into [batch_size by 784]
        # label is not one-hot encoded
        X = X.view(-1, 28 * 28).to(device)
        Y = Y.to(device)

        optimizer.zero_grad()
        hypothesis = model(X)
        cost = criterion(hypothesis, Y)
        cost.backward()
        optimizer.step()

        avg_cost += cost / total_batch

    print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost))

print('Learning finished')

# Test model and check accuracy
with torch.no_grad():
    model.train()

    # Test the model using test sets
    X_test = mnist_test.test_data.view(-1, 28 * 28).float().to(device)
    Y_test = mnist_test.test_labels.to(device)

    prediction = model(X_test)
    correct_prediction = torch.argmax(prediction, 1) == Y_test
    accuracy = correct_prediction.float().mean()
    print('Accuracy:', accuracy.item())