train_size = int(0.8*len(total_data))
test_size = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data,[train_size,test_size])
train_size,test_size

batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
                                       batch_size=batch_size,
                                       shuffle=True,
                                       num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                       batch_size=batch_size,
                                       shuffle=True,
                                       num_workers=1)

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]):
    npimg = imgs.numpy().transpose((1,2,0))
    npimg = npimg * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
    npimg = npimg.clip(0, 1)
    # 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)
    plt.axis('off')

# import torch.nn.functional as F
# num_classes = 4  # 图片的类别数
# class Network_bn(nn.Module):
#      def __init__(self):
#         super().__init__()
#          # 特征提取网络
#         self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0) 
#         self.bn1 = nn.BatchNorm2d(12)                
#         self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0) 
#         self.bn2 = nn.BatchNorm2d(12)
#         self.pool = nn.MaxPool2d(2,2)
#         self.conv3 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
#         self.bn3 = nn.BatchNorm2d(24) 
#         self.conv4 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
#         self.bn4 = nn.BatchNorm2d(24)  
#         # 分类网络
#         self.fc1 = nn.Linear(24*50*50,num_classes)
#      # 前向传播
#      def forward(self, x):
#         x = F.relu(self.bn1(self.conv1(x)))
#         x = F.relu(self.bn2(self.conv2(x)))
#         x = self.pool(x)
#         x = F.relu(self.bn3(self.conv3(x)))
#         x = F.relu(self.bn4(self.conv4(x)))
#         x = self.pool(x)
#         x = x.view(-1,24*50*50)
#         x = self.fc1(x)
#         return x
# model = Network_bn().to(device)
# model

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小，一共900张图片
    num_batches = len(dataloader)   # 批次数目，29（900/32）
    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

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小，一共10000张图片
    num_batches = len(dataloader)          # 批次数目，8（255/32=8，向上取整）
    test_loss, test_acc = 0, 0
    # 当不进行训练时，停止梯度更新，节省计算内存消耗
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)
            # 计算loss
            target_pred = model(imgs)
            loss        = loss_fn(target_pred, target)
            test_loss += loss.item()
            test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()
    test_acc  /= size
    test_loss /= num_batches
    return test_acc, test_loss

for param in model_ft.parameters():
    param.requires_grad = True
# 再继续训练所有的参数，学习率调小一点
optimizer = torch.optim.Adam(model_ft.parameters(), lr=1e-4)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.92)
# 损失函数
criterion = nn.CrossEntropyLoss()

import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False      # 用来正常显示负号
plt.rcParams['figure.dpi']         = 100        #分辨率
epochs_range = range(epochs)
plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

train_on_gpu = True
# 得到一个batch的测试数据
imgs, labels = next(iter(train_dl))
# 进行预测
model_ft.eval()
if train_on_gpu:
    output = model_ft(imgs.cuda())
else:
    output = model_ft(imgs)
# 获得预测结果(概率最大的)
_, preds_tensor = torch.max(output, 1)
preds = np.squeeze(preds_tensor.numpy()) if not train_on_gpu else np.squeeze(preds_tensor.cpu().numpy())
preds

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, 10)) 
for idx, imgs in enumerate(imgs[:10]):
    #ax = fig.add_subplot(rows, columns, idx+1, xticks=[], yticks=[])
    npimg = imgs.numpy().transpose((1,2,0))
    npimg = npimg * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
    npimg = npimg.clip(0, 1)
    # 将整个figure分成2行10列，绘制第i+1个子图。
    ax = plt.subplot(2, 5, idx+1)
    ax.set_title("{} ({})".format(classNames[preds[idx]], classNames[labels[idx]]),
                 color=("green" if classNames[preds[idx]]==classNames[labels[idx]] else "red"))
    plt.imshow(npimg)
    plt.axis('off')