import torch
from torch import nn
from d2l import torch as d2l

# 对某一层进行dropout处理
def dropout_layer(X, dropout):
    assert 0 <= dropout <= 1 # 不满足assert的条件会报错，满足条件则继续执行下面的语句
    if dropout == 1:
        return torch.zeros_like(X)
    if dropout == 0:
        return X
    mask = (torch.rand(X.shape) > dropout).float() # 生成布尔张量, 若随机数大于dropout, 则为1, 否则为0, 然后再转换为float类型
    return mask * X / (1.0 - dropout) # 为了保持期望不变，需要除以(1.0 - dropout)

# 定义模型参数
num_inputs, num_outputs, num_hiddens1, num_hiddens2 = 784, 10, 256, 256

# 定义模型
dropout1, dropout2 = 0.2, 0.5

class Net(nn.Module):
    def __init__(self, num_inputs, num_outputs, num_hiddens1, num_hiddens2, is_training=True):
        super(Net, self).__init__() # 调用基类的初始化方法
        self.num_inputs = num_inputs
        self.training = is_training
        self.lin1 = nn.Linear(num_inputs, num_hiddens1)
        self.lin2 = nn.Linear(num_hiddens1, num_hiddens2)
        self.lin3 = nn.Linear(num_hiddens2, num_outputs)
        self.relu = nn.ReLU()

    def forward(self, X):
        H1 = self.relu(self.lin1(X.reshape(-1, self.num_inputs)))
        # 只有训练模型时才使用暂退法
        if self.training == True:
            # 在第一个全连接层之后添加一个暂退层
            H1 = dropout_layer(H1, dropout1)
        H2 = self.relu(self.lin2(H1))
        if self.training == True:
            # 在第二个全连接层之后添加一个暂退层
            H2 = dropout_layer(H2, dropout2)
        out = self.lin3(H2)
        return out


net = Net(num_inputs, num_outputs, num_hiddens1, num_hiddens2)

# 训练与测试
num_epochs, lr, batch_size = 10, 0.5, 256
loss = nn.CrossEntropyLoss(reduction='none') # 交叉熵损失
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
trainer = torch.optim.SGD(net.parameters(), lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)

d2l.plt.show()