import torch
import torch.nn as nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
from torch.autograd import Variable

# Hyper Parameters
num_epochs = 5
batch_size = 100
learning_rate = 0.001
use_cuda = True if torch.cuda.is_available() else False

# MNIST Dataset
train_dataset = dsets.MNIST(root=r'E:\DataSets\mnist',
                            train=True,
                            transform=transforms.ToTensor(),
                            download=True)

test_dataset = dsets.MNIST(root=r'E:\DataSets\mnist',
                           train=False,
                           transform=transforms.ToTensor())

# Data Loader (Input Pipeline)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size,
                                          shuffle=False)


# CNN Model (2 conv layers)
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        # input size None * 1 * 28 * 28
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(2)
        )
        # size None * 16 * 14 * 14
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(2)
        )
        # size None * 32 * 7 * 7
        self.fc = nn.Linear(7 * 7 * 32, 10)
        # size None * 10

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out


cnn = CNN()

# Loss and Optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(cnn.parameters(), lr=learning_rate)

if use_cuda:
    cnn = cnn.cuda()
    criterion = criterion.cuda()

# Train the Model
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = Variable(images)
        labels = Variable(labels)

        if use_cuda:
            images = images.cuda()
            labels = labels.cuda()

        # Forward + Backward + Optimize
        optimizer.zero_grad()
        outputs = cnn(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        if (i + 1) % 100 == 0:
            print('Epoch [%d/%d], Iter [%d/%d] Loss: %.4f'
                  % (epoch + 1, num_epochs, i + 1, len(train_dataset) // batch_size, loss.data[0]))

# Test the Model
cnn.eval()  # Change model to 'eval' mode (BN uses moving mean/var).
correct = 0
total = 0
for images, labels in test_loader:
    images = Variable(images)
    if use_cuda:
        images = images.cuda()
    outputs = cnn(images)
    _, predicted = torch.max(outputs.cpu().data, 1)
    total += labels.size(0)
    correct += (predicted == labels).sum()

print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))

# Save the Trained Model
torch.save(cnn.state_dict(), 'cnn.pkl')