import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 8, 8)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(8, 16, 8)
        self.fc1 = nn.Linear(53824, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 12)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features

def imshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

def imgshow(loader):
    dataiter = iter(loader)
    inputs, labels = dataiter.next()
    imshow(torchvision.utils.make_grid(inputs))
    print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
    inputs = inputs.to(device)
    outputs = net(inputs)
    _, predicted = torch.max(outputs, 1)
    print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))

def accshow(loader, which):
    correct = 0
    total = 0
    with torch.no_grad():
        for data in loader:
            inputs, labels = data
            inputs = inputs.to(device)
            labels = labels.to(device)
            outputs = net(inputs)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('Accuracy of the network on the', which, 'images: %d %%' % (100 * correct / total))

def classaccshow(loader):
    class_correct = list(0. for i in range(classes_length))
    class_total = list(0. for i in range(classes_length))
    with torch.no_grad():
        for data in loader:
            inputs, labels = data
            inputs = inputs.to(device)
            labels = labels.to(device)
            outputs = net(inputs)
            _, predicted = torch.max(outputs, 1)
            c = (predicted == labels).squeeze()
            try:
                for i in range(classes_length*2):
                    label = labels[i]
                    class_correct[label] += c[i].item()
                    class_total[label] += 1
            except IndexError:
                pass
    for i in range(classes_length):
        print('Accuracy of %5s : %2d %%' % (classes[i], 100 * class_correct[i] / class_total[i]))

if __name__ == '__main__':

    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

    transform1 = transforms.Compose(
    [transforms.Resize((256, 256)),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
     ])

    transform2 = transforms.Compose(
    [transforms.Resize((256, 256)),
     transforms.RandomVerticalFlip(p=1),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
     ])

    transform3 = transforms.Compose(
    [transforms.Resize((256, 256)),
     transforms.ColorJitter(brightness=0, contrast=0, saturation=0, hue=0),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
     ])

    transform4 = transforms.Compose(
    [transforms.Resize((256, 256)),
     transforms.CenterCrop(256),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
     ])

    transform5 = transforms.Compose(
    [transforms.Resize((256, 256)),
     transforms.RandomVerticalFlip(p=1),
     transforms.ColorJitter(brightness=0, contrast=0, saturation=0, hue=0),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
     ])

    dataset1 = torchvision.datasets.ImageFolder(root='TRUNK12', transform=transform1, target_transform=None)
    dataset2 = torchvision.datasets.ImageFolder(root='TRUNK12', transform=transform2, target_transform=None)
    dataset3 = torchvision.datasets.ImageFolder(root='TRUNK12', transform=transform3, target_transform=None)
    dataset4 = torchvision.datasets.ImageFolder(root='TRUNK12', transform=transform4, target_transform=None)
    dataset5 = torchvision.datasets.ImageFolder(root='TRUNK12', transform=transform5, target_transform=None)
    dataset = dataset1 + dataset2 + dataset3 + dataset4 + dataset5
    dataset_length = dataset.__len__()
    trainset_length = int(0.7*dataset_length)
    testset_length = dataset_length - trainset_length
    trainset, testset = torch.utils.data.random_split(dataset, (trainset_length, testset_length))
    truetestset = torchvision.datasets.ImageFolder(root='test', transform=transform1, target_transform=None)
    batch_size = 10
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True, num_workers=2)
    testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size, shuffle=False, num_workers=2)
    truetestloader = torch.utils.data.DataLoader(truetestset, batch_size=4, shuffle=True, num_workers=2)

    classes = ('alder', 'beech', 'birch', 'chestnut', 'gingko biloba', 'hornbeam', 'horse chestnut', 'linden', 'oak', 'oriental plane', 'pine', 'spruce')
    classes_length = len(classes)

    net = Net()
    net = net.to(device)

    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9, weight_decay=0)
    scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=100, gamma=0.5)

    for epoch in range(100):  # loop over the dataset multiple times

        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            # get the inputs
            inputs, labels = data
            inputs = inputs.to(device)
            labels = labels.to(device)

            # zero the parameter gradients
            optimizer.zero_grad()

            # forward + backward + optimize
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()

            # print statistics
            running_loss += loss.item()
            if i % 100 == 99:
                print('[%d, %5d] loss: %.10f' %
                      (epoch + 1, i + 1, running_loss / 100))
                running_loss = 0.0

        if epoch % 5 == 4:
            accshow(trainloader, 'train')
            accshow(testloader, 'test')
            accshow(truetestloader, 'truetest')

        scheduler.step()
    print('Finished Training')

    classaccshow(testloader)

    accshow(truetestloader, 'truetest')
    classaccshow(truetestloader)
    imgshow(truetestloader)