import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

train_ds = torchvision.datasets.CIFAR10('data', 
                                      train=True, 
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)
test_ds  = torchvision.datasets.CIFAR10('data', 
                                      train=False, 
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)

train_ds = torchvision.datasets.CIFAR10('data', 
                                      train=True, 
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)
test_ds  = torchvision.datasets.CIFAR10('data', 
                                      train=False, 
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)

# 取一个批次查看数据格式
# 数据的shape为：[batch_size, channel, height, weight]
# 其中batch_size为自己设定，channel，height和weight分别是图片的通道数，高度和宽度。
imgs, labels = next(iter(train_dl))
imgs.shape

import numpy as np
 # 指定图片大小，图像大小为20宽、5高的绘图(单位为英寸inch)
plt.figure(figsize=(20, 5)) 
for i, imgs in enumerate(imgs[:20]):
    # 维度缩减
    npimg = imgs.numpy().transpose((1,2,0))
    # 将整个figure分成2行10列，绘制第i+1个子图。
    plt.subplot(2, 10, i+1)
    plt.imshow(npimg, cmap=plt.cm.binary)
    plt.axis('off')

import torch.nn.functional as F
num_classes = 10  # 图片的类别数
class Model(nn.Module):
     def __init__(self):
        super().__init__()
         # 特征提取网络
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3) 
        self.pool1 = nn.MaxPool2d(2)                
        self.conv2 = nn.Conv2d(64, 64, kernel_size=3) 
        self.pool2 = nn.MaxPool2d(2) 
        self.conv3 = nn.Conv2d(64, 128, kernel_size=3) 
        self.pool3 = nn.MaxPool2d(2) 
        # 分类网络
        self.fc1 = nn.Linear(512, 256)          
        self.fc2 = nn.Linear(256, num_classes)
     # 前向传播
     def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))     
        x = self.pool2(F.relu(self.conv2(x)))
        x = self.pool3(F.relu(self.conv3(x)))
        x = torch.flatten(x, start_dim=1)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小，一共60000张图片
    num_batches = len(dataloader)   # 批次数目，1875（60000/32）
    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率
    for X, y in dataloader:  # 获取图片及其标签
        X, y = X.to(device), y.to(device)
        # 计算预测误差
        pred = model(X)          # 网络输出
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失
        # 反向传播
        optimizer.zero_grad()  # grad属性归零
        loss.backward()        # 反向传播
        optimizer.step()       # 每一步自动更新
        # 记录acc与loss
        train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()
    train_acc  /= size
    train_loss /= num_batches
    return train_acc, train_loss

epochs     = 10
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []
for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')