从零丢弃法的实现

%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

print(torch.__version__)

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

X = torch.arange(16).view(2, 8)
dropout(X, 0)
dropout(X, 0.5)
dropout(X, 1.0)

# 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)

epoch 1, loss 0.0046, train acc 0.549, test acc 0.704
epoch 2, loss 0.0023, train acc 0.785, test acc 0.737
epoch 3, loss 0.0019, train acc 0.825, test acc 0.834
epoch 4, loss 0.0017, train acc 0.842, test acc 0.763
epoch 5, loss 0.0016, train acc 0.848, test acc 0.813