《动手学深度学习》第二次打卡

最新推荐文章于 2022-03-06 17:10:54 发布

nekomoon404

最新推荐文章于 2022-03-06 17:10:54 发布

阅读量328

点赞数

本文链接：https://blog.csdn.net/qq_36415639/article/details/104399343

版权

1.过拟合欠拟合及其解决方案

1.1概念

欠拟合（underfitting）：模型无法得到较低的训练误差；
过拟合（overfitting）：模型的误差远小于它在测试数据上的误差。

给定训练集，模型复杂度和误差之间的关系为：

在这里插入图片描述

1.2多项式函数拟合实验

%matplotlib inline
import torch
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)

初始化模型参数

n_train, n_test, true_w, true_b = 100, 100, [1.2, -3.4, 5.6], 5
features = torch.randn((n_train + n_test, 1))
poly_features = torch.cat((features, torch.pow(features, 2), torch.pow(features, 3)), 1) 
labels = (true_w[0] * poly_features[:, 0] + true_w[1] * poly_features[:, 1]
          + true_w[2] * poly_features[:, 2] + true_b)
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)

定义，训练和测试模型

def semilogy(x_vals, y_vals, x_label, y_label, x2_vals=None, y2_vals=None,
             legend=None, figsize=(3.5, 2.5)):
    # d2l.set_figsize(figsize)
    d2l.plt.xlabel(x_label)
    d2l.plt.ylabel(y_label)
    d2l.plt.semilogy(x_vals, y_vals)
    if x2_vals and y2_vals:
        d2l.plt.semilogy(x2_vals, y2_vals, linestyle=':')
        d2l.plt.legend(legend)

num_epochs, loss = 100, torch.nn.MSELoss()

def fit_and_plot(train_features, test_features, train_labels, test_labels):
    # 初始化网络模型
    net = torch.nn.Linear(train_features.shape[-1], 1)
    # 通过Linear文档可知，pytorch已经将参数初始化了，所以我们这里就不手动初始化了
    
    # 设置批量大小
    batch_size = min(10, train_labels.shape[0])    
    dataset = torch.utils.data.TensorDataset(train_features, train_labels)      # 设置数据集
    train_iter = torch.utils.data.DataLoader(dataset, batch_size, shuffle=True) # 设置获取数据方式
    
    optimizer = torch.optim.SGD(net.parameters(), lr=0.01)                      # 设置优化函数，使用的是随机梯度下降优化
    train_ls, test_ls = [], []
    for _ in range(num_epochs):
        for X, y in train_iter:                                                 # 取一个批量的数据
            l = loss(net(X), y.view(-1, 1))                                     # 输入到网络中计算输出，并和标签比较求得损失函数
            optimizer.zero_grad()                                               # 梯度清零，防止梯度累加干扰优化
            l.backward()                                                        # 求梯度
            optimizer.step()                                                    # 迭代优化函数，进行参数优化
        train_labels = train_labels.view(-1, 1)
        test_labels = test_labels.view(-1, 1)
        train_ls.append(loss(net(train_features), train_labels).item())         # 将训练损失保存到train_ls中
        test_ls.append(loss(net(test_features), test_labels).item())            # 将测试损失保存到test_ls中
    print('final epoch: train loss', train_ls[-1], 'test loss', test_ls[-1])    
    semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss',
             range(1, num_epochs + 1), test_ls, ['train', 'test'])
    print('weight:', net.weight.data,
          '\nbias:', net.bias.data)

1.3权重衰减

权重衰减等价于 $L_2$ 范数正则化，它是在模型原损失眼熟基础上添加 $L_2$ 范数惩罚项，即模型权重参数每个元素平方和与一个正常数的乘积。从而得到训练所需的最小化函数。

以高斯线性回归为例引入一个过拟合问题，并使用权重衰减来应对过拟合，用以下的线性函数来生成任一样本的标签。
$y=0.05+\sum^o_{i=1}0.01x_i+\epsilon y=0.05+\sum^o_{i=1}0.01x_i+\epsilon$

%matplotlib inline
import torch
import torch.nn as nn
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

初始化模型参数

n_train, n_test, num_inputs = 20, 100, 200
true_w, true_b = torch.ones(num_inputs, 1) * 0.01, 0.05

features = torch.randn((n_train + n_test, num_inputs))
labels = torch.matmul(features, true_w) + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)
train_features, test_features = features[:n_train, :], features[n_train:, :]
train_labels, test_labels = labels[:n_train], labels[n_train:]

# 定义参数初始化函数，初始化模型参数并且附上梯度
def init_params():
    w = torch.randn((num_inputs, 1), requires_grad=True)
    b = torch.zeros(1, requires_grad=True)
    return [w, b]

定义 $L_2$ 范数惩罚项

def l2_penalty(w):
    return (w**2).sum() / 2

定义训练和误差

batch_size, num_epochs, lr = 1, 100, 0.003
net, loss = d2l.linreg, d2l.squared_loss

dataset = torch.utils.data.TensorDataset(train_features, train_labels)
train_iter = torch.utils.data.DataLoader(dataset, batch_size, shuffle=True)

def fit_and_plot(lambd):
    w, b = init_params()
    train_ls, test_ls = [], []
    for _ in range(num_epochs):
        for X, y in train_iter:
            # 添加了L2范数惩罚项
            l = loss(net(X, w, b), y) + lambd * l2_penalty(w)
            l = l.sum()
            
            if w.grad is not None:
                w.grad.data.zero_()
                b.grad.data.zero_()
            l.backward()
            d2l.sgd([w, b], lr, batch_size)
        train_ls.append(loss(net(train_features, w, b), train_labels).mean().item())
        test_ls.append(loss(net(test_features, w, b), test_labels).mean().item())
    d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss',
                 range(1, num_epochs + 1), test_ls, ['train', 'test'])
    print('L2 norm of w:', w.norm().item())

简洁实现

def fit_and_plot_pytorch(wd):
    # 对权重参数衰减。权重名称一般是以weight结尾
    net = nn.Linear(num_inputs, 1)
    nn.init.normal_(net.weight, mean=0, std=1)
    nn.init.normal_(net.bias, mean=0, std=1)
    optimizer_w = torch.optim.SGD(params=[net.weight], lr=lr, weight_decay=wd) # 对权重参数衰减
    optimizer_b = torch.optim.SGD(params=[net.bias], lr=lr)  # 不对偏差参数衰减
    
    train_ls, test_ls = [], []
    for _ in range(num_epochs):
        for X, y in train_iter:
            l = loss(net(X), y).mean()
            optimizer_w.zero_grad()
            optimizer_b.zero_grad()
            
            l.backward()
            
            # 对两个optimizer实例分别调用step函数，从而分别更新权重和偏差
            optimizer_w.step()
            optimizer_b.step()
        train_ls.append(loss(net(train_features), train_labels).mean().item())
        test_ls.append(loss(net(test_features), test_labels).mean().item())
    d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss',
                 range(1, num_epochs + 1), test_ls, ['train', 'test'])
    print('L2 norm of w:', net.weight.data.norm().item())

1.4.丢弃法

多层感知机中神经网络图描述了一个单隐藏层的多层感知机，隐藏单元 $h_i=\phi(x_1w_{1i}+x_2w_{2i}+x_3w_{3i}+x_4w_{4i}+b)$ ，当对该隐藏层使用丢弃法时，该层的隐藏单元将有一定概率被丢弃掉，设丢弃概率为 $p$ ，则 $h_i$ 有 $p$ 的概率被清零，有 $1 - p$ 的概率除以 $1 - p$ 做拉伸，丢弃法不改变其输入的期望值。

丢弃法从零开始的实现

%matplotlib inline
import torch
import torch.nn as nn
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

def dropout(X, drop_prob):
    X = X.float()
    assert 0 <= drop_prob <= 1
    keep_prob = 1 - drop_prob
    # 这种情况下把全部元素都丢弃
    if keep_prob == 0:
        return torch.zeros_like(X)
    mask = (torch.rand(X.shape) < keep_prob).float()
    
    return mask * X / keep_prob

# 参数的初始化
num_inputs, num_outputs, num_hiddens1, num_hiddens2 = 784, 10, 256, 256

W1 = torch.tensor(np.random.normal(0, 0.01, size=(num_inputs, num_hiddens1)), dtype=torch.float, requires_grad=True)
b1 = torch.zeros(num_hiddens1, requires_grad=True)
W2 = torch.tensor(np.random.normal(0, 0.01, size=(num_hiddens1, num_hiddens2)), dtype=torch.float, requires_grad=True)
b2 = torch.zeros(num_hiddens2, requires_grad=True)
W3 = torch.tensor(np.random.normal(0, 0.01, size=(num_hiddens2, num_outputs)), dtype=torch.float, requires_grad=True)
b3 = torch.zeros(num_outputs, requires_grad=True)

params = [W1, b1, W2, b2, W3, b3]

drop_prob1, drop_prob2 = 0.2, 0.5

def net(X, is_training=True):
    X = X.view(-1, num_inputs)
    H1 = (torch.matmul(X, W1) + b1).relu()
    if is_training:  # 只在训练模型时使用丢弃法
        H1 = dropout(H1, drop_prob1)  # 在第一层全连接后添加丢弃层
    H2 = (torch.matmul(H1, W2) + b2).relu()
    if is_training:
        H2 = dropout(H2, drop_prob2)  # 在第二层全连接后添加丢弃层
    return torch.matmul(H2, W3) + b3

def evaluate_accuracy(data_iter, net):
    acc_sum, n = 0.0, 0
    for X, y in data_iter:
        if isinstance(net, torch.nn.Module):
            net.eval() # 评估模式, 这会关闭dropout
            acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
            net.train() # 改回训练模式
        else: # 自定义的模型
            if('is_training' in net.__code__.co_varnames): # 如果有is_training这个参数
                # 将is_training设置成False
                acc_sum += (net(X, is_training=False).argmax(dim=1) == y).float().sum().item() 
            else:
                acc_sum += (net(X).argmax(dim=1) == y).float().sum().item() 
        n += y.shape[0]
    return acc_sum / n

num_epochs, lr, batch_size = 5, 100.0, 256  # 这里的学习率设置的很大，原因与之前相同。
loss = torch.nn.CrossEntropyLoss()
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, root='/home/kesci/input/FashionMNIST2065')
d2l.train_ch3(
    net,
    train_iter,
    test_iter,
    loss,
    num_epochs,
    batch_size,
    params,
    lr)

丢弃法的简洁实现

net = nn.Sequential(
        d2l.FlattenLayer(),
        nn.Linear(num_inputs, num_hiddens1),
        nn.ReLU(),
        nn.Dropout(drop_prob1),
        nn.Linear(num_hiddens1, num_hiddens2), 
        nn.ReLU(),
        nn.Dropout(drop_prob2),
        nn.Linear(num_hiddens2, 10)
        )

for param in net.parameters():
    nn.init.normal_(param, mean=0, std=0.01)

2.梯度消失与梯度爆炸

深度模型有关数值稳定性的典型问题是消失（vanishing）和爆炸（explosion）。当神经网络的层数较多时，模型的数值稳定性容易变差。设一个层数为 $L$ 的多层感知机所有隐藏层的激活函数为恒等映射，给定输入 $X$ ，第 $l$ 层的输出 $H^{(l)}=XW^{(1)}W^{(2)} \dots W^{(l)}$ ，假设输入和所有输出层的权重参数都是标量，如权重参数为0.2和5，则第30层输出为输入 $X$ 分别于 $0.2^{30}$ （消失）和 $5^{30}$ （爆炸）的乘积。

3.Kaggle房价预测实战

%matplotlib inline
import torch
import torch.nn as nn
import numpy as np
import pandas as pd
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
torch.set_default_tensor_type(torch.FloatTensor)

获取和读取数据集
比赛数据分为训练数据集和测试数据集。两个数据集都包括每栋房子的特征，如街道类型、建造年份、房顶类型、地下室状况等特征值。这些特征值有连续的数字、离散的标签甚至是缺失值“na”。只有训练数据集包括了每栋房子的价格，也就是标签。我们将通过pandas库读入并处理数据。

test_data = pd.read_csv("/home/kesci/input/houseprices2807/house-prices-advanced-regression-techniques/test.csv")
train_data = pd.read_csv("/home/kesci/input/houseprices2807/house-prices-advanced-regression-techniques/train.csv")

预处理数据
我们对连续数值的特征做标准化（standardization）：设该特征在整个数据集上的均值为，标准差为。那么，我们可以将该特征的每个值先减去 $\mu$ 再除以 $\sigma$ 得到标准化后的每个特征值。对于缺失的特征值，我们将其替换成该特征的均值。

numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index
all_features[numeric_features] = all_features[numeric_features].apply(
    lambda x: (x - x.mean()) / (x.std()))
# 标准化后，每个数值特征的均值变为0，所以可以直接用0来替换缺失值
all_features[numeric_features] = all_features[numeric_features].fillna(0)

接下来将离散数值转成指示特征。举个例子，假设特征MSZoning里面有两个不同的离散值RL和RM，那么这一步转换将去掉MSZoning特征，并新加两个特征MSZoning_RL和MSZoning_RM，其值为0或1。如果一个样本原来在MSZoning里的值为RL，那么有MSZoning_RL=1且MSZoning_RM=0。

# dummy_na=True将缺失值也当作合法的特征值并为其创建指示特征
all_features = pd.get_dummies(all_features, dummy_na=True)
all_features.shape

最后，通过values属性得到NumPy格式的数据，并转成Tensor方便后面的训练。

n_train = train_data.shape[0]
train_features = torch.tensor(all_features[:n_train].values, dtype=torch.float)
test_features = torch.tensor(all_features[n_train:].values, dtype=torch.float)
train_labels = torch.tensor(train_data.SalePrice.values, dtype=torch.float).view(-1, 1)

训练模型
比赛用来评价模型的对数均方根误差:
$\sqrt{\frac{1}{n} \sum^n_{i=1} \left( \log (y_i)-\log (\hat{y}_i) \right)^2 }$

loss = torch.nn.MSELoss()

def get_net(feature_num):
    net = nn.Linear(feature_num, 1)
    for param in net.parameters():
        nn.init.normal_(param, mean=0, std=0.01)
    return net
    
def log_rmse(net, features, labels):
    with torch.no_grad():
        # 将小于1的值设成1，使得取对数时数值更稳定
        clipped_preds = torch.max(net(features), torch.tensor(1.0))
        rmse = torch.sqrt(2 * loss(clipped_preds.log(), labels.log()).mean())
    return rmse.item()
    
def train(net, train_features, train_labels, test_features, test_labels,
          num_epochs, learning_rate, weight_decay, batch_size):
    train_ls, test_ls = [], []
    dataset = torch.utils.data.TensorDataset(train_features, train_labels)
    train_iter = torch.utils.data.DataLoader(dataset, batch_size, shuffle=True)
    # 这里使用了Adam优化算法
    optimizer = torch.optim.Adam(params=net.parameters(), lr=learning_rate, weight_decay=weight_decay) 
    net = net.float()
    for epoch in range(num_epochs):
        for X, y in train_iter:
            l = loss(net(X.float()), y.float())
            optimizer.zero_grad()
            l.backward()
            optimizer.step()
        train_ls.append(log_rmse(net, train_features, train_labels))
        if test_labels is not None:
            test_ls.append(log_rmse(net, test_features, test_labels))
    return train_ls, test_ls

K折交叉验证
$K$ 折交叉验证被用来选择模型设计并调节超参数。下面实现了一个函数，它返回第i折交叉验证时所需要的训练和验证数据。

def get_k_fold_data(k, i, X, y):
    # 返回第i折交叉验证时所需要的训练和验证数据
    assert k > 1
    fold_size = X.shape[0] // k
    X_train, y_train = None, None
    for j in range(k):
        idx = slice(j * fold_size, (j + 1) * fold_size)
        X_part, y_part = X[idx, :], y[idx]
        if j == i:
            X_valid, y_valid = X_part, y_part
        elif X_train is None:
            X_train, y_train = X_part, y_part
        else:
            X_train = torch.cat((X_train, X_part), dim=0)
            y_train = torch.cat((y_train, y_part), dim=0)
    return X_train, y_train, X_valid, y_valid

在 $K$ 折交叉验证中我们训练 $K$ 次并返回训练和验证的平均误差

def k_fold(k, X_train, y_train, num_epochs,
           learning_rate, weight_decay, batch_size):
    train_l_sum, valid_l_sum = 0, 0
    for i in range(k):
        data = get_k_fold_data(k, i, X_train, y_train)
        net = get_net(X_train.shape[1])
        train_ls, valid_ls = train(net, *data, num_epochs, learning_rate,
                                   weight_decay, batch_size)
        train_l_sum += train_ls[-1]
        valid_l_sum += valid_ls[-1]
        if i == 0:
            d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse',
                         range(1, num_epochs + 1), valid_ls,
                         ['train', 'valid'])
        print('fold %d, train rmse %f, valid rmse %f' % (i, train_ls[-1], valid_ls[-1]))
    return train_l_sum / k, valid_l_sum / k

模型选择
使用一组未经调优的超参数并计算交叉验证误差，可以改动这些超参数来尽可能减小平均测试误差。由于过拟合的存在，当训练误差降低时，我们要观察折交叉验证上的误差是否也相应降低。

k, num_epochs, lr, weight_decay, batch_size = 5, 100, 5, 0, 64
train_l, valid_l = k_fold(k, train_features, train_labels, num_epochs, lr, weight_decay, batch_size)
print('%d-fold validation: avg train rmse %f, avg valid rmse %f' % (k, train_l, valid_l))

预测并在Kaggle中提交结果

def train_and_pred(train_features, test_features, train_labels, test_data,
                   num_epochs, lr, weight_decay, batch_size):
    net = get_net(train_features.shape[1])
    train_ls, _ = train(net, train_features, train_labels, None, None,
                        num_epochs, lr, weight_decay, batch_size)
    d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse')
    print('train rmse %f' % train_ls[-1])
    preds = net(test_features).detach().numpy()
    test_data['SalePrice'] = pd.Series(preds.reshape(1, -1)[0])
    submission = pd.concat([test_data['Id'], test_data['SalePrice']], axis=1)
    submission.to_csv('./submission.csv', index=False)
    # sample_submission_data = pd.read_csv("../input/house-prices-advanced-regression-techniques/sample_submission.csv")

4.循环网络进阶

4.1GRU

⻔控循环神经⽹络：捕捉时间序列中时间步距离较⼤的依赖关系，在在PyTorch中我们直接调用nn模块中的GRU类即可。

lr = 1e-2 # 注意调整学习率
gru_layer = nn.GRU(input_size=vocab_size, hidden_size=num_hiddens)
model = d2l.RNNModel(gru_layer, vocab_size).to(device)
d2l.train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                                corpus_indices, idx_to_char, char_to_idx,
                                num_epochs, num_steps, lr, clipping_theta,
                                batch_size, pred_period, pred_len, prefixes)

4.2长短期记忆（LSTM）

LSTM 中引入了3个门，即输入门（input gate）、遗忘门（forget gate）和输出门（output gate），以及与隐藏状态形状相同的记忆细胞（某些文献把记忆细胞当成一种特殊的隐藏状态），从而记录额外的信息。

def lstm(inputs, state, params):
    [W_xi, W_hi, b_i, W_xf, W_hf, b_f, W_xo, W_ho, b_o, W_xc, W_hc, b_c, W_hq, b_q] = params
    (H, C) = state
    outputs = []
    for X in inputs:
        I = torch.sigmoid(torch.matmul(X, W_xi) + torch.matmul(H, W_hi) + b_i)
        F = torch.sigmoid(torch.matmul(X, W_xf) + torch.matmul(H, W_hf) + b_f)
        O = torch.sigmoid(torch.matmul(X, W_xo) + torch.matmul(H, W_ho) + b_o)
        C_tilda = torch.tanh(torch.matmul(X, W_xc) + torch.matmul(H, W_hc) + b_c)
        C = F * C + I * C_tilda
        H = O * C.tanh()
        Y = torch.matmul(H, W_hq) + b_q
        outputs.append(Y)
    return outputs, (H, C)
#训练模型
num_epochs, num_steps, batch_size, lr, clipping_theta = 160, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 40, 50, ['分开', '不分开']

d2l.train_and_predict_rnn(lstm, get_params, init_lstm_state, num_hiddens,
                          vocab_size, device, corpus_indices, idx_to_char,
                          char_to_idx, False, num_epochs, num_steps, lr,
                          clipping_theta, batch_size, pred_period, pred_len,
                          prefixes)

简洁实现

num_hiddens=256
num_epochs, num_steps, batch_size, lr, clipping_theta = 160, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 40, 50, ['分开', '不分开']

lr = 1e-2 # 注意调整学习率
lstm_layer = nn.LSTM(input_size=vocab_size, hidden_size=num_hiddens)
model = d2l.RNNModel(lstm_layer, vocab_size)
d2l.train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                                corpus_indices, idx_to_char, char_to_idx,
                                num_epochs, num_steps, lr, clipping_theta,
                                batch_size, pred_period, pred_len, prefixes)

4.3深度循环神经网络

在深度学习应用里，我们通常会用到含有多个隐藏层的循环神经网络，也称作深度循环神经网络。

num_hiddens=256
num_epochs, num_steps, batch_size, lr, clipping_theta = 160, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 40, 50, ['分开', '不分开']

lr = 1e-2 # 注意调整学习率

gru_layer = nn.LSTM(input_size=vocab_size, hidden_size=num_hiddens,num_layers=2)
model = d2l.RNNModel(gru_layer, vocab_size).to(device)
d2l.train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                                corpus_indices, idx_to_char, char_to_idx,
                                num_epochs, num_steps, lr, clipping_theta,
                                batch_size, pred_period, pred_len, prefixes)

4.4双向循环神经网络

之前介绍的循环神经网络模型都是假设当前时间步是由前面的较早时间步的序列决定的，因此它们都将信息通过隐藏状态从前往后传递。有时候，当前时间步也可能由后面时间步决定，双向循环神经网络通过增加从后往前传递信息的隐藏层来更灵活地处理这类信息。

num_hiddens=128
num_epochs, num_steps, batch_size, lr, clipping_theta = 160, 35, 32, 1e-2, 1e-2
pred_period, pred_len, prefixes = 40, 50, ['分开', '不分开']

lr = 1e-2 # 注意调整学习率

gru_layer = nn.GRU(input_size=vocab_size, hidden_size=num_hiddens,bidirectional=True)
model = d2l.RNNModel(gru_layer, vocab_size).to(device)
d2l.train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                                corpus_indices, idx_to_char, char_to_idx,
                                num_epochs, num_steps, lr, clipping_theta,
                                batch_size, pred_period, pred_len, prefixes)

nekomoon404

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
《动手学深度学习》第二次打卡

1.过拟合欠拟合及其解决方案1.1概念欠拟合（underfitting）：模型无法得到较低的训练误差；过拟合（overfitting）：模型的误差远小于它在测试数据上的误差。给定训练集，模型复杂度和误差之间的关系为：1.2多项式函数拟合实验%matplotlib inlineimport torchimport numpy as npimport syssys.path....
复制链接

扫一扫