Attention

注意力不需要训练

n_train = 50  # 训练样本数
x_train, _ = torch.sort(torch.rand(n_train) * 5)   
# 排序后的训练样本

def f(x):
    return 2 * torch.sin(x) + x**0.8

y_train = f(x_train) + torch.normal(0.0, 0.5, (n_train,))  # 训练样本的输出
x_test = torch.arange(0, 5, 0.1)  # 测试样本
y_truth = f(x_test)  # 测试样本的真实输出
n_test = len(x_test)  # 测试样本数
# X_tile的形状:(n_train，n_train)，每一行都包含着相同的训练输入
X_tile = x_train.repeat((n_train, 1))
# Y_tile的形状:(n_train，n_train)，每一行都包含着相同的训练输出
Y_tile = y_train.repeat((n_train, 1))
# keys的形状:('n_train'，'n_train'-1)
keys = X_tile[(1 - torch.eye(n_train)).type(torch.bool)].reshape((n_train, -1))
#torch.eye返回对角线为1的矩阵
# values的形状:('n_train'，'n_train'-1)，第i行去掉第i个数值，获得n_train组不同的数据
values = Y_tile[(1 - torch.eye(n_train)).type(torch.bool)].reshape((n_train, -1))
net(x_train, keys, values)

# net查看的是造出来的数据和x_train数据之间的差值 距离越大贡献越小
class NWKernelRegression(nn.Module):
    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.w = nn.Parameter(torch.rand((1,), requires_grad=True))

    def forward(self, queries, keys, values):
        # queries和attention_weights的形状为(查询个数，“键－值”对个数)
        queries = queries.repeat_interleave(keys.shape[1]).reshape((-1, keys.shape[1]))
        self.attention_weights = nn.functional.softmax(
            -((queries - keys) * self.w)**2 / 2, dim=1)
        # values的形状为(查询个数，“键－值”对个数)
        return torch.bmm(self.attention_weights.unsqueeze(1),values.unsqueeze(-1)).reshape(-1)