本文共 10516 字，大约阅读时间需要 35 分钟。

Transform：数据的预处理/数据增强

补充：数据增强（对数据集进行变换，丰富数据集，从而使模型更具泛化能力）

数据增强一

1.

数据增强二

1.

torchvision.transforms :常用的图像预处理方法

上面的三个数据包为pytorch的视觉工具包中的主要工具包，还是比较重要的

torchvision.transforms :常用的图像预处理方法

• 数据中心化
• 数据标准化
• 缩放
• 裁剪
• 旋转
• 翻转
• 填充
• 噪声添加
• 灰度变换
• 线性变换
• 仿射变换
• 亮度、饱和度及对比度变换

import torchimport torch.nn as nnimport matplotlib.pyplot as pltimport numpy as nptorch.manual_seed(10)lr = 0.01  # 学习率# 生成虚拟数据sample_nums = 100mean_value = 1.7bias = 5         # 5n_data = torch.ones(sample_nums, 2)x0 = torch.normal(mean_value * n_data, 1) + bias      # 类别0 数据 shape=(100, 2)y0 = torch.zeros(sample_nums)                         # 类别0 标签 shape=(100, 1)x1 = torch.normal(-mean_value * n_data, 1) + bias     # 类别1 数据 shape=(100, 2)y1 = torch.ones(sample_nums)                          # 类别1 标签 shape=(100, 1)train_x = torch.cat((x0, x1), 0)train_y = torch.cat((y0, y1), 0)# 定义模型class LR(nn.Module):    def __init__(self):        super(LR, self).__init__()        self.features = nn.Linear(2, 1)        self.sigmoid = nn.Sigmoid()    def forward(self, x):        x = self.features(x)        x = self.sigmoid(x)        return xlr_net = LR()# 定义损失函数与优化器loss_fn = nn.BCELoss()optimizer = torch.optim.SGD(lr_net.parameters(), lr=0.01, momentum=0.9)for iteration in range(1000):    # 前向传播    y_pred = lr_net(train_x)    # 计算 MSE loss    loss = loss_fn(y_pred, train_y)    # 反向传播    loss.backward()    # 更新参数    optimizer.step()    # 清空梯度    optimizer.zero_grad()    # 绘图    if iteration % 40 == 0:        mask = y_pred.ge(0.5).float().squeeze()  # 以0.5为阈值进行分类        correct = (mask == train_y).sum()  # 计算正确预测的样本个数        acc = correct.item() / train_y.size(0)  # 计算精度        plt.scatter(x0.data.numpy()[:, 0], x0.data.numpy()[:, 1], c='r', label='class 0')        plt.scatter(x1.data.numpy()[:, 0], x1.data.numpy()[:, 1], c='b', label='class 1')        w0, w1 = lr_net.features.weight[0]        w0, w1 = float(w0.item()), float(w1.item())        plot_b = float(lr_net.features.bias[0].item())        plot_x = np.arange(-6, 6, 0.1)        plot_y = (-w0 * plot_x - plot_b) / w1        plt.xlim(-5, 10)        plt.ylim(-7, 10)        plt.plot(plot_x, plot_y)        plt.text(-5, 5, 'Loss=%.4f' % loss.data.numpy(), fontdict={   'size': 20, 'color': 'red'})        plt.title("Iteration: {}\nw0:{:.2f} w1:{:.2f} b: {:.2f} accuracy:{:.2%}".format(iteration, w0, w1, plot_b, acc))        plt.legend()        plt.show()        plt.pause(0.5)        if acc > 0.99:            break

将数据的均值变为0 ，标准差变为1

为什么进行标准化，为了加快模型的收敛（改逻辑回归的bias可知）

Transform图像增强

import osimport numpy as npimport torchimport randomfrom torch.utils.data import DataLoaderimport torchvision.transforms as transformsfrom tools.my_dataset import RMBDatasetfrom PIL import Imagefrom matplotlib import pyplot as pltdef set_seed(seed=1):    random.seed(seed)    np.random.seed(seed)    torch.manual_seed(seed)    torch.cuda.manual_seed(seed)set_seed(1)  # 设置随机种子# 参数设置MAX_EPOCH = 10BATCH_SIZE = 1LR = 0.01log_interval = 10val_interval = 1rmb_label = {   "1": 0, "100": 1}def transform_invert(img_, transform_train):    """    将data 进行反transfrom操作    :param img_: tensor    :param transform_train: torchvision.transforms    :return: PIL image    """    if 'Normalize' in str(transform_train):        norm_transform = list(filter(lambda x: isinstance(x, transforms.Normalize), transform_train.transforms))        mean = torch.tensor(norm_transform[0].mean, dtype=img_.dtype, device=img_.device)        std = torch.tensor(norm_transform[0].std, dtype=img_.dtype, device=img_.device)        img_.mul_(std[:, None, None]).add_(mean[:, None, None])    img_ = img_.transpose(0, 2).transpose(0, 1)  # C*H*W --> H*W*C    img_ = np.array(img_) * 255    if img_.shape[2] == 3:        img_ = Image.fromarray(img_.astype('uint8')).convert('RGB')    elif img_.shape[2] == 1:        img_ = Image.fromarray(img_.astype('uint8').squeeze())    else:        raise Exception("Invalid img shape, expected 1 or 3 in axis 2, but got {}!".format(img_.shape[2]) )    return img_# ============================ step 1/5 数据 ============================split_dir = os.path.join("..", "..", "data", "rmb_split")train_dir = os.path.join(split_dir, "train")valid_dir = os.path.join(split_dir, "valid")norm_mean = [0.485, 0.456, 0.406]norm_std = [0.229, 0.224, 0.225]train_transform = transforms.Compose([    transforms.Resize((224, 224)),    # 1 CenterCrop    # transforms.CenterCrop(512),     # 512    # 2 RandomCrop    # transforms.RandomCrop(224, padding=16),    # transforms.RandomCrop(224, padding=(16, 64)),    # transforms.RandomCrop(224, padding=16, fill=(255, 0, 0)),    # transforms.RandomCrop(512, pad_if_needed=True),   # pad_if_needed=True    # transforms.RandomCrop(224, padding=64, padding_mode='edge'),    # transforms.RandomCrop(224, padding=64, padding_mode='reflect'),    # transforms.RandomCrop(1024, padding=1024, padding_mode='symmetric'),    # 3 RandomResizedCrop    # transforms.RandomResizedCrop(size=224, scale=(0.5, 0.5)),    # 4 FiveCrop    # transforms.FiveCrop(112),    # transforms.Lambda(lambda crops: torch.stack([(transforms.ToTensor()(crop)) for crop in crops])),    # 5 TenCrop    # transforms.TenCrop(112, vertical_flip=False),    # transforms.Lambda(lambda crops: torch.stack([(transforms.ToTensor()(crop)) for crop in crops])),    # 1 Horizontal Flip    # transforms.RandomHorizontalFlip(p=1),    # 2 Vertical Flip    # transforms.RandomVerticalFlip(p=0.5),    # 3 RandomRotation    # transforms.RandomRotation(90),    # transforms.RandomRotation((90), expand=True),    # transforms.RandomRotation(30, center=(0, 0)),    # transforms.RandomRotation(30, center=(0, 0), expand=True),   # expand only for center rotation    transforms.ToTensor(),    transforms.Normalize(norm_mean, norm_std),])valid_transform = transforms.Compose([    transforms.Resize((224, 224)),    transforms.ToTensor(),    transforms.Normalize(norm_mean, norm_std)])# 构建MyDataset实例train_data = RMBDataset(data_dir=train_dir, transform=train_transform)valid_data = RMBDataset(data_dir=valid_dir, transform=valid_transform)# 构建DataLodertrain_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)# ============================ step 5/5 训练 ============================for epoch in range(MAX_EPOCH):    for i, data in enumerate(train_loader):        inputs, labels = data   # B C H W        img_tensor = inputs[0, ...]     # C H W        img = transform_invert(img_tensor, train_transform)        plt.imshow(img)        plt.show()        plt.pause(0.5)        plt.close()        # bs, ncrops, c, h, w = inputs.shape        # for n in range(ncrops):        #     img_tensor = inputs[0, n, ...]  # C H W        #     img = transform_invert(img_tensor, train_transform)        #     plt.imshow(img)        #     plt.show()        #     plt.pause(1)

import osimport numpy as npimport torchimport randomfrom matplotlib import pyplot as pltfrom torch.utils.data import DataLoaderimport torchvision.transforms as transformsfrom tools.my_dataset import RMBDatasetfrom tools.common_tools import transform_invertdef set_seed(seed=1):    random.seed(seed)    np.random.seed(seed)    torch.manual_seed(seed)    torch.cuda.manual_seed(seed)set_seed(1)  # 设置随机种子# 参数设置MAX_EPOCH = 10BATCH_SIZE = 1LR = 0.01log_interval = 10val_interval = 1rmb_label = {   "1": 0, "100": 1}# ============================ step 1/5 数据 ============================split_dir = os.path.join("..", "..", "data", "rmb_split")train_dir = os.path.join(split_dir, "train")valid_dir = os.path.join(split_dir, "valid")norm_mean = [0.485, 0.456, 0.406]norm_std = [0.229, 0.224, 0.225]train_transform = transforms.Compose([    transforms.Resize((224, 224)),    # 1 Pad    # transforms.Pad(padding=32, fill=(255, 0, 0), padding_mode='constant'),    # transforms.Pad(padding=(8, 64), fill=(255, 0, 0), padding_mode='constant'),    # transforms.Pad(padding=(8, 16, 32, 64), fill=(255, 0, 0), padding_mode='constant'),    # transforms.Pad(padding=(8, 16, 32, 64), fill=(255, 0, 0), padding_mode='symmetric'),    # 2 ColorJitter    # transforms.ColorJitter(brightness=0.5),    # transforms.ColorJitter(contrast=0.5),    # transforms.ColorJitter(saturation=0.5),    # transforms.ColorJitter(hue=0.3),    # 3 Grayscale    # transforms.Grayscale(num_output_channels=3),    # 4 Affine    # transforms.RandomAffine(degrees=30),    # transforms.RandomAffine(degrees=0, translate=(0.2, 0.2), fillcolor=(255, 0, 0)),    # transforms.RandomAffine(degrees=0, scale=(0.7, 0.7)),    # transforms.RandomAffine(degrees=0, shear=(0, 0, 0, 45)),    # transforms.RandomAffine(degrees=0, shear=90, fillcolor=(255, 0, 0)),    # 5 Erasing    # transforms.ToTensor(),    # transforms.RandomErasing(p=1, scale=(0.02, 0.33), ratio=(0.3, 3.3), value=(254/255, 0, 0)),    # transforms.RandomErasing(p=1, scale=(0.02, 0.33), ratio=(0.3, 3.3), value='1234'),    # 1 RandomChoice    # transforms.RandomChoice([transforms.RandomVerticalFlip(p=1), transforms.RandomHorizontalFlip(p=1)]),    # 2 RandomApply    # transforms.RandomApply([transforms.RandomAffine(degrees=0, shear=45, fillcolor=(255, 0, 0)),    #                         transforms.Grayscale(num_output_channels=3)], p=0.5),    # 3 RandomOrder    # transforms.RandomOrder([transforms.RandomRotation(15),    #                         transforms.Pad(padding=32),    #                         transforms.RandomAffine(degrees=0, translate=(0.01, 0.1), scale=(0.9, 1.1))]),    transforms.ToTensor(),    transforms.Normalize(norm_mean, norm_std),])valid_transform = transforms.Compose([    transforms.Resize((224, 224)),    transforms.ToTensor(),    transforms.Normalize(norm_mean, norm_std)])# 构建MyDataset实例train_data = RMBDataset(data_dir=train_dir, transform=train_transform)valid_data = RMBDataset(data_dir=valid_dir, transform=valid_transform)# 构建DataLodertrain_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)# ============================ step 5/5 训练 ============================for epoch in range(MAX_EPOCH):    for i, data in enumerate(train_loader):        inputs, labels = data   # B C H W        img_tensor = inputs[0, ...]     # C H W        img = transform_invert(img_tensor, train_transform)        plt.imshow(img)        plt.show()        plt.pause(0.5)        plt.close()