import torch
from torch.autograd import Variable
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F

import torchvision
import torchvision.transforms as transforms
# The output of torchvision datasets are PILImage images of range [0, 1].
# We transform them to Tensors of normalized range [-1, 1]
transform=transforms.Compose([transforms.ToTensor(),
                              transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
                             ])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=1,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=1,
                                          shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')





class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        self.dconv1 = nn.Conv2d(3, 6, 5)
        self.dpool  = nn.MaxPool2d(2,2)
        self.dconv2 = nn.Conv2d(6, 16, 5)
        self.dfc1   = nn.Linear(16*5*5, 16*6*5*5)

        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool  = nn.MaxPool2d(2,2)
        self.fc1   = nn.Linear(16*5*5, 120)
        self.fc2   = nn.Linear(120, 84)
        self.fc3   = nn.Linear(84, 10)

    def forward(self, x):
        y = x.clone()
        x = self.pool(F.relu(self.dconv1(x)))
        x = self.pool(F.relu(self.dconv2(x)))
        x = x.view(-1, 16*5*5)
        x = F.relu(self.dfc1(x))
        x=x.view(16,6,5,5)

        conv2 = nn.Conv2d(6,16,5)
        conv2.weight.copy_(x)
        conv2.bias.data.zero_()

        y = self.pool(F.relu(self.conv1(y)))
        y = self.pool(F.relu(conv2(y)))
        y = y.view(-1, 16*5*5)
        y = F.relu(self.fc1(y))
        y = F.relu(self.fc2(y))
        y = self.fc3(y)
        return y

net = Net()




criterion = nn.CrossEntropyLoss() # use a Classification Cross-Entropy loss
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

for epoch in range(2): # loop over the dataset multiple times

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

        # wrap them in Variable
        inputs, labels = Variable(inputs), Variable(labels)

        # 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.data[0]
        if i % 2000 == 1999: # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' % (epoch+1, i+1, running_loss / 2000))
            running_loss = 0.0
print('Finished Training')