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

class Block(nn.Module):
    '''Depthwise conv + Pointwise conv'''
    def __init__(self, in_planes, out_planes, stride=1):
        super(Block, self).__init__()
        # Depthwise 卷積，3*3 的卷積核，分為 in_planes，即各層單獨進行卷積
        self.conv1 = nn.Conv2d(in_planes, in_planes, kernel_size=3, stride=stride, padding=1, groups=in_planes, bias=False)
        self.bn1 = nn.BatchNorm2d(in_planes)
        # Pointwise 卷積，1*1 的卷積核
        self.conv2 = nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn2 = nn.BatchNorm2d(out_planes)

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = F.relu(self.bn2(self.conv2(out)))
        return out

# 使用GPU訓練，可以在選單 "程式碼執行工具" -> "更改執行時型別" 裡進行設定
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])

transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,  download=True, transform=transform_train)
testset  = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform_test)

trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=2)
testloader = torch.utils.data.DataLoader(testset, batch_size=128, shuffle=False, num_workers=2)

class MobileNetV1(nn.Module):
    # (128,2) means conv planes=128, stride=2
    cfg = [(64,1), (128,2), (128,1), (256,2), (256,1), (512,2), (512,1), 
           (1024,2), (1024,1)]

    def __init__(self, num_classes=10):
        super(MobileNetV1, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(32)
        self.layers = self._make_layers(in_planes=32)
        self.linear = nn.Linear(1024, num_classes)

    def _make_layers(self, in_planes):
        layers = []
        for x in self.cfg:
            out_planes = x[0]
            stride = x[1]
            layers.append(Block(in_planes, out_planes, stride))
            in_planes = out_planes
        return nn.Sequential(*layers)

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.layers(out)
        out = F.avg_pool2d(out, 2)
        out = out.view(out.size(0), -1)
        out = self.linear(out)
        return out

# 網路放到GPU上
net = MobileNetV1().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)

for epoch in range(10):  # 重複多輪訓練
    for i, (inputs, labels) in enumerate(trainloader):
        inputs = inputs.to(device)
        labels = labels.to(device)
        # 優化器梯度歸零
        optimizer.zero_grad()
        # 正向傳播 +　反向傳播 + 優化 
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        # 輸出統計資訊
        if i % 100 == 0:   
            print('Epoch: %d Minibatch: %5d loss: %.3f' %(epoch + 1, i + 1, loss.item()))

print('Finished Training')

correct = 0
total = 0

for data in testloader:
    images, labels = data
    images, labels = images.to(device), labels.to(device)
    outputs = net(images)
    _, predicted = torch.max(outputs.data, 1)
    total += labels.size(0)
    correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %.2f %%' % (
    100 * correct / total))