环境+数据的读取

深度学习重要的部分-查看虚拟环境-命令

conda env list

激活环境，DL为虚拟环境

conda activate DL#激活
conda deactivate#退出

数据读取

在这里插入代码片
class FlowerDataset(Dataset):
    def __init__(self, root_dir, ann_file, transform=None):
        self.ann_file = ann_file
        self.root_dir = root_dir
        self.img_label = self.load_annotations()
        self.img = [os.path.join(self.root_dir, img) for img in list(self.img_label.keys())]
        self.label = [label for label in list(self.img_label.values())]
        self.transform = transform

    def __len__(self):
        return len(self.img)

    def __getitem__(self, idx):
        image = Image.open(self.img[idx])
        label = self.label[idx]
        if self.transform:
            image = self.transform(image)
        label = torch.from_numpy(np.array(label))
        return image, label

    def load_annotations(self):
        data_infos = {}
        with open(self.ann_file) as f:
            samples = [x.strip().split(' ') for x in f.readlines()]
            for filename, gt_label in samples:
                data_infos[filename] = np.array(gt_label, dtype=np.int64)
        return data_infos

data_transforms = {
    'train':
        transforms.Compose([
        transforms.Resize(64),
        transforms.RandomRotation(45),#随机旋转，-45到45度之间随机选
        transforms.CenterCrop(64),#从中心开始裁剪
        transforms.RandomHorizontalFlip(p=0.5),#随机水平翻转 选择一个概率概率
        transforms.RandomVerticalFlip(p=0.5),#随机垂直翻转
        transforms.ColorJitter(brightness=0.2, contrast=0.1, saturation=0.1, hue=0.1),#参数1为亮度，参数2为对比度，参数3为饱和度，参数4为色相
        transforms.RandomGrayscale(p=0.025),#概率转换成灰度率，3通道就是R=G=B
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])#均值，标准差
    ]),
    'valid':
        transforms.Compose([
        transforms.Resize(64),
        transforms.CenterCrop(64),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}
data_dir = './flower_data/'
train_dir = data_dir + '/train_filelist'
print(train_dir)
valid_dir = data_dir + '/val_filelist'
train_dataset = FlowerDataset(root_dir=train_dir, ann_file = './flower_data/train.txt', transform=data_transforms['train'])
val_dataset = FlowerDataset(root_dir=valid_dir, ann_file = './flower_data/val.txt', transform=data_transforms['valid'])
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
val_loader = DataLoader(val_dataset, batch_size=64, shuffle=True)

训练模型

def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False, filename='best.pth'):
    since = time.time()
    best_acc = 0
    model.to(device)

    val_acc_history = []
    train_acc_history = []
    train_losses = []
    valid_losses = []
    LRs = [optimizer.param_groups[0]['lr']]

    best_model_wts = copy.deepcopy(model.state_dict())

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # 训练和验证
        for phase in ['train', 'valid']:
            if phase == 'train':
                model.train()  # 训练
            else:
                model.eval()   # 验证

            running_loss = 0.0
            running_corrects = 0

            # 把数据都取个遍
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # 清零
                optimizer.zero_grad()
                # 只有训练的时候计算和更新梯度
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    loss = criterion(outputs, labels)
                    _, preds = torch.max(outputs, 1)
                    #print(loss)

                    # 训练阶段更新权重
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # 计算损失
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / len(dataloaders[phase].dataset)
            epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
            
            
            time_elapsed = time.time() - since
            print('Time elapsed {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
            

            # 得到最好那次的模型
            if phase == 'valid' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())
                state = {
                  'state_dict': model.state_dict(),#字典里key就是各层的名字，值就是训练好的权重
                  'best_acc': best_acc,
                  'optimizer' : optimizer.state_dict(),#优化器的状态信息
                }
                torch.save(state, filename)
            if phase == 'valid':
                val_acc_history.append(epoch_acc)
                valid_losses.append(epoch_loss)
                scheduler.step(epoch_loss)#学习率衰减
            if phase == 'train':
                train_acc_history.append(epoch_acc)
                train_losses.append(epoch_loss)
        
        print('Optimizer learning rate : {:.7f}'.format(optimizer.param_groups[0]['lr']))
        LRs.append(optimizer.param_groups[0]['lr'])
        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
    print('Best val Acc: {:4f}'.format(best_acc))

    # 训练完后用最好的一次当做模型最终的结果,等着一会测试
    model.load_state_dict(best_model_wts)
    return model, val_acc_history, train_acc_history, valid_losses, train_losses, LRs