import torch
from torch import nn
from torchvision import datasets, transforms
from torch.nn import functional as F
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
from matplotlib_inline import backend_inline
from IPython import display
import time

def load_data_fashion_mnist(batch_size, resize=None):
    """Download the Fashion-MNIST dataset and then load it into memory.

    Defined in :numref:`sec_utils`"""
    trans = [transforms.ToTensor()]
    if resize:
        trans.insert(0, transforms.Resize(resize))
    trans = transforms.Compose(trans)
    mnist_train = datasets.FashionMNIST(
        root="../data", train=True, transform=trans, download=True)
    mnist_test = datasets.FashionMNIST(
        root="../data", train=False, transform=trans, download=True)
    return (torch.utils.data.DataLoader(mnist_train, batch_size, shuffle=True,
                                        num_workers=4),
            torch.utils.data.DataLoader(mnist_test, batch_size, shuffle=False,
                                        num_workers=4))

class Accumulator:
    """For accumulating sums over `n` variables."""
    def __init__(self, n):
        """Defined in :numref:`sec_utils`"""
        self.data = [0.0] * n

    def add(self, *args):
        self.data = [a + float(b) for a, b in zip(self.data, args)]

    def reset(self):
        self.data = [0.0] * len(self.data)

    def __getitem__(self, idx):
        return self.data[idx]
    
def accuracy(y_hat, y):
    """返回预测正确的样本个数（float 类型）"""
    # 如果 y_hat 是 logits 或概率（如 [N, C]），取预测类别
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = torch.argmax(y_hat, dim=1) 
    
    # 比较预测 vs 真实标签，并确保类型一致（避免 int64 vs int32 问题）
    cmp = (y_hat.to(y.dtype) == y)
    
    # 求 cmp 中 True 的个数（True=1, False=0）
    return float(cmp.sum())  # cmp.sum() 等价于 torch.sum(cmp)

def evaluate_accuracy_gpu(net, data_iter, device=None):
    if isinstance(net, nn.Module):
        net.eval()
        if not device:
            device = next(iter(net.parameters())).device
    metric = Accumulator(2)
    with torch.no_grad():
        for X, y in data_iter:
            if isinstance(X, list):
                X = [x.to(device) for x in X]
            else:
                X = X.to(device)
            y = y.to(device)
            metric.add(accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]

class Animator:
    def __init__(self, xlabel = None, ylabel = None, legend = None,
                 xlim = None, ylim = None, xscale = 'linear', yscale = 'linear',
                 fmts = ('-', 'm--', 'g-.', 'r:'), nrows = 1, ncols = 1,
                 figsize = (3.5, 2.5)):
        if legend is None:
            legend = []
        backend_inline.set_matplotlib_formats('svg')
        self.fig, self.axes = plt.subplots(nrows, ncols, figsize=figsize)
        if nrows * ncols == 1:
            self.axes = [self.axes, ]
        self.config_axes = lambda: self.set_axes(self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
        self.X, self.Y, self.fmts = None, None, fmts
    def set_axes(self, axes, xlabel, ylabel, xlim, ylim, xscale, yscale, legend):
        axes.set_xlabel(xlabel)
        axes.set_ylabel(ylabel)
        axes.set_xlim(xlim)
        axes.set_ylim(ylim)
        axes.set_xscale(xscale)
        axes.set_yscale(yscale)
        if legend:
            axes.legend(legend)
        axes.grid()
    
    def add(self, x, y):
        if not hasattr(y, '__len__'):
            y = [y]
        n = len(y)
        if not hasattr(x, '__len__'):
            x = [x] * n
        if not self.X:
            self.X = [[] for _ in range(n)]
        if not self.Y:
            self.Y = [[] for _ in range(n)]
        for i, (a, b) in enumerate(zip(x, y)):
            if a is not None and b is not None:
                self.X[i].append(a)
                self.Y[i].append(b)
        self.axes[0].cla()
        for x, y, fmt in zip(self.X, self.Y, self.fmts):
            self.axes[0].plot(x, y , fmt)
        self.config_axes()
        display.display(self.fig)
        display.clear_output(wait=True)

## 模型
class Residual(nn.Module):
    def __init__(self, input_channels, num_channels,
                 use_1x1conv=False, strides=1):
        super().__init__()
        self.conv1 = nn.Conv2d(input_channels, num_channels,
                               kernel_size=3, padding=1, stride=strides)
        self.conv2 = nn.Conv2d(num_channels, num_channels,
                               kernel_size=3, padding=1)
        if use_1x1conv:
            self.conv3 = nn.Conv2d(input_channels, num_channels,
                                   kernel_size=1, stride=strides)
        else:
            self.conv3 = None
        self.bn1 = nn.BatchNorm2d(num_channels)
        self.bn2 = nn.BatchNorm2d(num_channels)

    def forward(self, X):
        Y = F.relu(self.bn1(self.conv1(X)))
        Y = self.bn2(self.conv2(Y))
        if self.conv3:
            X = self.conv3(X)
        Y += X
        return F.relu(Y)


def resnet_block(input_channels, num_channels, num_residuals, first_block=False):
    blk = []
    for i in range(num_residuals):
        if i == 0 and not first_block:
            blk.append(Residual(input_channels, num_channels,
                                use_1x1conv=True, strides=2))
        else:
            blk.append(Residual(num_channels, num_channels))
    return blk


b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.BatchNorm2d(64), nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))

net = nn.Sequential(b1, b2, b3, b4, b5,
                    nn.AdaptiveAvgPool2d((1,1)),
                    nn.Flatten(), nn.Linear(512, 10))


def train(net, train_iter, test_iter, num_epochs, lr, device):
    def init_weights(m):
        if type(m) == nn.Linear or type(m) == nn.Conv2d:
            nn.init.xavier_uniform_(m.weight)

    net.apply(init_weights)
    print('training on', device)
    net.to(device)
    optimizer = torch.optim.SGD(net.parameters(), lr=lr)
    loss = nn.CrossEntropyLoss()
    animator = Animator(xlabel='epoch', xlim=[1, num_epochs],
                            legend=['train loss', 'train acc', 'test acc'])
    timers = []
    num_batches = len(train_iter)
    for epoch in range(num_epochs):
        metric = Accumulator(3)
        net.train()
        for i, (X, y) in enumerate(train_iter):
            timer = time.time()
            optimizer.zero_grad()
            X, y = X.to(device), y.to(device)
            y_hat = net(X)
            l = loss(y_hat, y)
            l.backward()
            optimizer.step()
            with torch.no_grad():
                metric.add(l * X.shape[0], accuracy(y_hat, y), X.shape[0])

            timers.append(time.time() - timer)
            train_l = metric[0] / metric[2]
            train_acc = metric[1] / metric[2]
            if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
                animator.add(epoch + (i + 1) / num_batches,
                             (train_l, train_acc, None))
        test_acc = evaluate_accuracy_gpu(net, test_iter)
        animator.add(epoch + 1, (None, None, test_acc))
        print(f'loss {train_l:.3f}, train acc {train_acc:.3f}, '
            f'test acc {test_acc:.3f}')
    print(f'{metric[2] * num_epochs / sum(timers):.1f} examples/sec '
          f'on {str(device)}')
   
lr, num_epochs, batch_size = 0.1, 10, 256
train_iter, test_iter = load_data_fashion_mnist(batch_size, resize=96)
train(net, train_iter, test_iter, num_epochs, lr, torch.device('cuda' if torch.cuda.is_available() else 'cpu'))