动手学深度学习-RNN-Transformer

class MultiHeadAttention(nn.Module):
    def __init__(self, key_size, query_size, value_size, num_hiddens, num_heads, dropout, bias=False, **kwargs):
        super(MultiHeadAttention, self).__init__(**kwargs)
        # TODO: 头数
        self.num_heads = num_heads
        # TODO: 注意力层
        self.attention = DotProductAttention(dropout)
        # TODO: 学习query, key value的投影矩阵(即线性层),以及
        self.W_q = nn.Linear(query_size, num_hiddens, bias=bias)
        self.W_k = nn.Linear(key_size, num_hiddens, bias=bias)
        self.W_v = nn.Linear(value_size, num_hiddens, bias=bias)
        self.W_o = nn.Linear(num_hiddens, num_hiddens, bias=bias)

    def forward(self, queries, keys, values, valid_lens):
        # queries，keys，values的形状:
        # (batch_size，查询或者“键－值”对的个数，num_hiddens)
        # valid_lens　的形状:
        # (batch_size，)或(batch_size，查询的个数)
        # 经过变换后，输出的queries，keys，values　的形状:
        # (batch_size*num_heads，查询或者“键－值”对的个数，
        # num_hiddens/num_heads)
        queries = transpose_qkv(self.W_q(queries), self.num_heads)
        keys = transpose_qkv(self.W_k(keys), self.num_heads)
        values = transpose_qkv(self.W_v(values), self.num_heads)

        if valid_lens is not None:
            # 在轴0，将第一项（标量或者矢量）复制num_heads次，
            # 然后如此复制第二项，然后诸如此类。
            valid_lens = torch.repeat_interleave(
                valid_lens, repeats=self.num_heads, dim=0)

        # output的形状:(batch_size*num_heads，查询的个数，
        # num_hiddens/num_heads)
        output = self.attention(queries, keys, values, valid_lens)

        # output_concat的形状:(batch_size，查询的个数，num_hiddens)
        output_concat = transpose_output(output, self.num_heads)
        return self.W_o(output_concat)

import torch
from d2l import torch as d2l


def show_heatmaps(matrices, xlabel, ylabel, titles=None, figsize=(2.5, 2.5), cmap='Reds'):
    """显示矩阵热图"""
    d2l.use_svg_display()
    num_rows, num_cols = matrices.shape[0], matrices.shape[1]
    fig, axes = d2l.plt.subplots(
        num_rows, num_cols, figsize=figsize, sharex=True, sharey=True, squeeze=False)

    for i, (row_axes, row_matrices) in enumerate(zip(axes, matrices)):
        for j, (ax, matrix) in enumerate(zip(row_axes, row_matrices)):
            pcm = ax.imshow(matrix.detach().numpy(), cmap=cmap)
            if i == num_rows - 1:
                ax.set_xlabel(xlabel)
            if j == 0:
                ax.set_ylabel(ylabel)
            if titles:
                ax.set_title(titles[j])

        fig.colorbar(pcm, ax=axes, shrink=0.6)


attention_weight = torch.eye(10).reshape((1, 1, 10, 10))
show_heatmaps(attention_weight, xlabel='Keys', ylabel='Queries')
d2l.plt.show()

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_repeat的形状:(n_test,n_train),
# 每一行都包含着相同的测试输入（例如：同样的查询）
X_repeat = x_test.repeat_interleave(n_train).reshape((-1, n_train))
# x_train包含着键。attention_weights的形状：(n_test,n_train),
# 每一行都包含着要在给定的每个查询的值（y_train）之间分配的注意力权重
attention_weights = nn.functional.softmax(-(X_repeat - x_train)**2 / 2, dim=1)
# y_hat的每个元素都是值的加权平均值，其中的权重是注意力权重
y_hat = torch.matmul(attention_weights, y_train)
plot_kernel_reg(y_hat)
d2l.plt.show()

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)

# 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))
# values的形状:('n_train'，'n_train'-1)
values = Y_tile[(1 - torch.eye(n_train)).type(torch.bool)
                ].reshape((n_train, -1))

net = NWKernelRegression()
loss = nn.MSELoss(reduction='none')
trainer = torch.optim.SGD(net.parameters(), lr=0.5)
animator = d2l.Animator(xlabel='epoch', ylabel='loss', xlim=[1, 5])

for epoch in range(5):
    trainer.zero_grad()
    l = loss(net(x_train, keys, values), y_train)
    l.sum().backward()
    trainer.step()
    print(f'epoch {epoch + 1}, loss {float(l.sum()):.6f}')
    animator.add(epoch + 1, float(l.sum()))

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

num_hiddens, num_heads = 100, 5
attention = d2l.MultiHeadAttention(num_hiddens, num_hiddens, num_hiddens,
                                   num_hiddens, num_heads, 0.5)
print(attention.eval())

batch_size, num_queries, valid_lens = 2, 4, torch.tensor([3, 2])
X = torch.ones((batch_size, num_queries, num_hiddens))
print(attention(X, X, X, valid_lens).shape)

class PositionalEncoding(nn.Module):
    """位置编码"""
    def __init__(self, num_hiddens, dropout, max_len=1000):
        super(PositionalEncoding, self).__init__()
        self.dropout = nn.Dropout(dropout)
        # 创建一个足够长的P
        self.P = torch.zeros((1, max_len, num_hiddens))
        X = torch.arange(max_len, dtype=torch.float32).reshape(
            -1, 1) / torch.pow(10000, torch.arange(
            0, num_hiddens, 2, dtype=torch.float32) / num_hiddens)
        self.P[:, :, 0::2] = torch.sin(X)
        self.P[:, :, 1::2] = torch.cos(X)

    def forward(self, X):
        X = X + self.P[:, :X.shape[1], :].to(X.device)
        return self.dropout(X)
 
encoding_dim, num_steps = 32, 60
pos_encoding = PositionalEncoding(encoding_dim, 0)
pos_encoding.eval()
X = pos_encoding(torch.zeros((1, num_steps, encoding_dim)))
P = pos_encoding.P[:, :X.shape[1], :]
d2l.plot(torch.arange(num_steps), P[0, :, 6:10].T, xlabel='Row (position)',
         figsize=(6, 2.5), legend=["Col %d" % d for d in torch.arange(6, 10)])
d2l.plt.show()

P = P[0, :, :].unsqueeze(0).unsqueeze(0)
d2l.show_heatmaps(P, xlabel='Column (encoding dimension)',
                  ylabel='Row (position)', figsize=(3.5, 4), cmap='Blues')

d2l.plt.show()