pytorch Dropout過擬合的操作

Posted on by

如下所示：

import torch
from torch.autograd import Variable
import matplotlib.pyplot as plt
torch.manual_seed(1)
N_SAMPLES = 20
N_HIDDEN = 300
# training data
x = torch.unsqueeze(torch.linspace(-1, 1, N_SAMPLES), 1)
y = x + 0.3 * torch.normal(torch.zeros(N_SAMPLES, 1), torch.ones(N_SAMPLES, 1))
x, y = Variable(x), Variable(y)
# test data
test_x = torch.unsqueeze(torch.linspace(-1, 1, N_SAMPLES), 1)
test_y = test_x + 0.3 * torch.normal(torch.zeros(N_SAMPLES, 1), torch.ones(N_SAMPLES, 1))
test_x = Variable(test_x, volatile=True)
test_y = Variable(test_y, volatile=True)
# show data
# plt.scatter(x.data.numpy(), y.data.numpy(), c='magenta', s=50, alpha=0.5, label='train')
# plt.scatter(test_x.data.numpy(), test_y.data.numpy(), c='cyan', s=50, alpha=0.5, label='test')
# plt.legend(loc='upper left')
# plt.ylim((-2.5, 2.5))
# plt.show()
net_overfitting = torch.nn.Sequential(
    torch.nn.Linear(1, N_HIDDEN),
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, N_HIDDEN),
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, 1),
)
net_dropped = torch.nn.Sequential(
    torch.nn.Linear(1, N_HIDDEN),
    torch.nn.Dropout(0.5),
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, N_HIDDEN),
    torch.nn.Dropout(0.5),
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, 1),
)
print(net_overfitting)
print(net_dropped)
optimizer_ofit = torch.optim.Adam(
    net_overfitting.parameters(),
    lr = 0.01,
)
optimizer_drop = torch.optim.Adam(
    net_dropped.parameters(),
    lr = 0.01,
)
loss_func = torch.nn.MSELoss()
plt.ion()
for t in range(500):
    pred_ofit = net_overfitting(x)
    pred_drop = net_dropped(x)
    loss_ofit = loss_func(pred_ofit, y)
    loss_drop = loss_func(pred_drop, y)
    optimizer_ofit.zero_grad()
    optimizer_drop.zero_grad()
    loss_ofit.backward()
    loss_drop.backward()
    optimizer_ofit.step()
    optimizer_drop.step()
    if t % 10 == 0:
        net_overfitting.eval()
        net_dropped.eval()
        plt.cla()
        test_pred_ofit = net_overfitting(test_x)
        test_pred_drop = net_dropped(test_x)
        plt.scatter(x.data.numpy(), y.data.numpy(), c='magenta', s=50, alpha=0.3, label='train')
        plt.scatter(test_x.data.numpy(), test_y.data.numpy(), c='cyan', s=50, alpha=0.3, label='test')
        plt.plot(test_x.data.numpy(), test_pred_ofit.data.numpy(), 'r-', lw=3, label='overfitting')
        plt.plot(test_x.data.numpy(), test_pred_drop.data.numpy(), 'b--', lw=3, label='dropout(50%)')
        plt.text(0, -1.2, 'overfitting loss=%.4f' % loss_func(test_pred_ofit, test_y).data[0], fontdict={'size': 20, 'color':  'red'})
        plt.text(0, -1.5, 'dropout loss=%.4f' % loss_func(test_pred_drop, test_y).data[0], fontdict={'size': 20, 'color': 'blue'})
        plt.legend(loc='upper left'); plt.ylim((-2.5, 2.5));plt.pause(0.1)
        net_overfitting.train()
        net_dropped.train()
plt.ioff()
plt.show()

補充：pytorch避免過擬合-dropout丟棄法的實現

對於一個單隱藏層的多層感知機，其中輸入個數為4，隱藏單元個數為5，且隱藏單元的計算表達式為：

開始實現drop丟棄法避免過擬合

定義dropout函數：

%matplotlib inline
import torch
import torch.nn as nn
import numpy as np
def dropout(X, drop_prob):
    X = X.float()
    assert 0 <= drop_prob <= 1
    keep_prob = 1 - drop_prob
    # 這種情況下把全部元素都丟棄
    if keep_prob == 0:
        return torch.zeros_like(X)
    mask = (torch.rand(X.shape) < keep_prob).float()
    return mask * X / keep_prob

定義模型參數：

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]

定義模型將全連接層和激活函數ReLU串起來，並對每個激活函數的輸出使用丟棄法。

分別設置各個層的丟棄概率。通常的建議是把靠近輸入層的丟棄概率設得小一點。

在這個實驗中，我們把第一個隱藏層的丟棄概率設為0.2，把第二個隱藏層的丟棄概率設為0.5。

我們可以通過參數is_training來判斷運行模式為訓練還是測試，並隻在訓練模式下使用丟棄法。

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:  # 隻在訓練模型時使用丟棄法
        H1 = dropout(H1, drop_prob1)  # 在第一層全連接後添加丟棄層
    H2 = (torch.matmul(H1, W2) + b2).relu()
    if is_training:
        H2 = dropout(H2, drop_prob2)  # 在第二層全連接後添加丟棄層
    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() # 評估模式, 這會關閉dropout
            acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
            net.train() # 改回訓練模式
        else: # 自定義的模型
            if('is_training' in net.__code__.co_varnames): # 如果有is_training這個參數
                # 將is_training設置成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

訓練和測試模型：

num_epochs, lr, batch_size = 5, 100.0, 256
loss = torch.nn.CrossEntropyLoss()
def load_data_fashion_mnist(batch_size, resize=None, root='~/Datasets/FashionMNIST'):
    """Download the fashion mnist dataset and then load into memory."""
    trans = []
    if resize:
        trans.append(torchvision.transforms.Resize(size=resize))
    trans.append(torchvision.transforms.ToTensor())
    
    transform = torchvision.transforms.Compose(trans)
    mnist_train = torchvision.datasets.FashionMNIST(root=root, train=True, download=True, transform=transform)
    mnist_test = torchvision.datasets.FashionMNIST(root=root, train=False, download=True, transform=transform)
    if sys.platform.startswith('win'):
        num_workers = 0  # 0表示不用額外的進程來加速讀取數據
    else:
        num_workers = 4
    train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
    test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)
    return train_iter, test_iter
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
              params=None, lr=None, optimizer=None):
    for epoch in range(num_epochs):
        train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
        for X, y in train_iter:
            y_hat = net(X)
            l = loss(y_hat, y).sum()
            
            # 梯度清零
            if optimizer is not None:
                optimizer.zero_grad()
            elif params is not None and params[0].grad is not None:
                for param in params:
                    param.grad.data.zero_()
            
            l.backward()
            if optimizer is None:
                sgd(params, lr, batch_size)
            else:
                optimizer.step()  # “softmax回歸的簡潔實現”一節將用到
            
            
            train_l_sum += l.item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
            n += y.shape[0]
        test_acc = evaluate_accuracy(test_iter, net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
              % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
train_iter, test_iter = load_data_fashion_mnist(batch_size)
train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr)

以上為個人經驗，希望能給大傢一個參考，也希望大傢多多支持WalkonNet。

推薦閱讀：