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
from torch.utils.data import Dataset


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5, 2, 2)
        self.pool = nn.MaxPool2d(3, 2)
        self.conv2 = nn.Conv2d(6, 16, 5, 2, 2)
        self.fc1 = nn.Linear(784, 240)
        self.fc2 = nn.Linear(240, 84)
        self.fc3 = nn.Linear(84, 12)
        self.dropout = nn.Dropout(p=0.5)

    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 = self.dropout(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

class Memory(Dataset):
    def __init__(self, dataset_array, dataset_labels):
        self.labels = dataset_labels.astype(np.float64)
        self.images = dataset_array.astype(np.float64)
    def __len__(self):
        return self.images.shape[0]
    def __getitem__(self, idx):
        return self.images[idx], self.labels[idx]

def training(epochs, lr, weight_decay, step_size, gamma):
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=lr, momentum=0.9, weight_decay=weight_decay)
    scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=step_size, gamma=gamma)

    print("Training started...")
    for epoch in range(epochs):  # 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.float().to(device)
            labels = labels.long().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 % int((trainset_length // batch_size) / 1) == int(((trainset_length // batch_size) / 1) - 1):
                print('Epoch [%d / %d], Step: %d, Loss: %.10f' %
                      (epoch + 1, epochs, i + 1, running_loss / int((trainset_length // batch_size) / 1)))
                running_loss = 0.0

        if epoch % 5 == 4:
            accshow(trainloader, 'train')
            accshow(cvloader, 'cross-validation')
            accshow(testloader, 'test')

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

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.float().to(device)
            labels = labels.long().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.float().to(device)
            labels = labels.long().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((128, 128)),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
     ])

    transform2 = transforms.Compose(
    [transforms.Resize((128, 128)),
     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((128, 128)),
     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.CenterCrop(128),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
     ])

    transform5 = transforms.Compose(
    [transforms.Resize((128, 128)),
     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)

    batch_size = 20

    print("Data loading...")
    dataset = dataset1 #+ dataset2 + dataset3 + dataset4 + dataset5
    dataset_length = dataset.__len__()
    datasetloader = torch.utils.data.DataLoader(dataset, batch_size=dataset_length, shuffle=False)
    dataset_array = next(iter(datasetloader))[0].numpy()
    dataset_labels = next(iter(datasetloader))[1].numpy()
    dataset_m = Memory(dataset_array, dataset_labels)

    trainset_length = int(0.7*dataset_length)
    cvset_length = dataset_length - trainset_length
    trainset, cvset = torch.utils.data.random_split(dataset_m, (trainset_length, cvset_length))
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True)
    cvloader = torch.utils.data.DataLoader(cvset, batch_size=batch_size, shuffle=False)

    testset = torchvision.datasets.ImageFolder(root='test', transform=transform1, target_transform=None)
    testset_length = testset.__len__()
    testsetloader = torch.utils.data.DataLoader(testset, batch_size=testset_length, shuffle=False)
    testset_array = next(iter(testsetloader))[0].numpy()
    testset_labels = next(iter(testsetloader))[1].numpy()
    testset_m = Memory(testset_array, testset_labels)
    testloader = torch.utils.data.DataLoader(testset_m, batch_size=testset_length, shuffle=False)
    testloader2 = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=True)
    print("Data loaded.")

    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)

    training(epochs=400, lr=0.001, weight_decay=0, step_size=200, gamma=0.1)

    classaccshow(cvloader)

    accshow(testloader, 'test')
    classaccshow(testloader)
    imgshow(testloader2)