王半仙的学习分享

#@save
def masked_softmax(X, valid_lens):
    """通过在最后一个轴上掩蔽元素来执行softmax操作"""
    # X:3D张量，valid_lens:1D或2D张量
    if valid_lens is None:
        return nn.functional.softmax(X, dim=-1)
    else:
        shape = X.shape
        if valid_lens.dim() == 1:
            valid_lens = torch.repeat_interleave(valid_lens, shape[1])
        else:
            valid_lens = valid_lens.reshape(-1)
        # 最后一轴上被掩蔽的元素使用一个非常大的负值替换，从而其softmax输出为0
        X = d2l.sequence_mask(X.reshape(-1, shape[-1]), valid_lens,
                              value=-1e6)
        return nn.functional.softmax(X.reshape(shape), dim=-1)

#@save
class AdditiveAttention(nn.Module):
    """加性注意力"""
    def __init__(self, key_size, query_size, num_hiddens, dropout, **kwargs):
        super(AdditiveAttention, self).__init__(**kwargs)
        self.W_k = nn.Linear(key_size, num_hiddens, bias=False)
        self.W_q = nn.Linear(query_size, num_hiddens, bias=False)
        self.w_v = nn.Linear(num_hiddens, 1, bias=False)
        self.dropout = nn.Dropout(dropout)

    def forward(self, queries, keys, values, valid_lens):
        queries, keys = self.W_q(queries), self.W_k(keys)
        # 在维度扩展后，
        # queries的形状：(batch_size，查询的个数，1，num_hidden)
        # key的形状：(batch_size，1，“键－值”对的个数，num_hiddens)
        # 使用广播方式进行求和
        features = queries.unsqueeze(2) + keys.unsqueeze(1)
        features = torch.tanh(features)
        # self.w_v仅有一个输出，因此从形状中移除最后那个维度。
        # scores的形状：(batch_size，查询的个数，“键-值”对的个数)
        scores = self.w_v(features).squeeze(-1)
        self.attention_weights = masked_softmax(scores, valid_lens)
        # values的形状：(batch_size，“键－值”对的个数，值的维度)
        return torch.bmm(self.dropout(self.attention_weights), values)

#@save
class DotProductAttention(nn.Module):
    """缩放点积注意力"""
    def __init__(self, dropout, **kwargs):
        super(DotProductAttention, self).__init__(**kwargs)
        self.dropout = nn.Dropout(dropout)

    # queries的形状：(batch_size，查询的个数，d)
    # keys的形状：(batch_size，“键－值”对的个数，d)
    # values的形状：(batch_size，“键－值”对的个数，值的维度)
    # valid_lens的形状:(batch_size，)或者(batch_size，查询的个数)
    def forward(self, queries, keys, values, valid_lens=None):
        d = queries.shape[-1]
        # 设置transpose_b=True为了交换keys的最后两个维度
        scores = torch.bmm(queries, keys.transpose(1,2)) / math.sqrt(d)
        self.attention_weights = masked_softmax(scores, valid_lens)
        return torch.bmm(self.dropout(self.attention_weights), values)

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

#@save
class AttentionDecoder(d2l.Decoder):
    """带有注意力机制解码器的基本接口"""
    def __init__(self, **kwargs):
        super(AttentionDecoder, self).__init__(**kwargs)

    @property
    def attention_weights(self):
        raise NotImplementedError

class Seq2SeqAttentionDecoder(AttentionDecoder):
    def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
                 dropout=0, **kwargs):
        super(Seq2SeqAttentionDecoder, self).__init__(**kwargs)
        self.attention = d2l.AdditiveAttention(
            num_hiddens, num_hiddens, num_hiddens, dropout)
        self.embedding = nn.Embedding(vocab_size, embed_size)
        self.rnn = nn.GRU(
            embed_size + num_hiddens, num_hiddens, num_layers,
            dropout=dropout)
        self.dense = nn.Linear(num_hiddens, vocab_size)

    def init_state(self, enc_outputs, enc_valid_lens, *args):
        # outputs的形状为(batch_size，num_steps，num_hiddens).
        # hidden_state的形状为(num_layers，batch_size，num_hiddens)
        outputs, hidden_state = enc_outputs
        return (outputs.permute(1, 0, 2), hidden_state, enc_valid_lens)

    def forward(self, X, state):
        # enc_outputs的形状为(batch_size,num_steps,num_hiddens).
        # hidden_state的形状为(num_layers,batch_size,
        # num_hiddens)
        enc_outputs, hidden_state, enc_valid_lens = state
        # 输出X的形状为(num_steps,batch_size,embed_size)
        X = self.embedding(X).permute(1, 0, 2)
        outputs, self._attention_weights = [], []
        for x in X:
            # query的形状为(batch_size,1,num_hiddens)
            query = torch.unsqueeze(hidden_state[-1], dim=1)
            # context的形状为(batch_size,1,num_hiddens)
            context = self.attention(
                query, enc_outputs, enc_outputs, enc_valid_lens)
            # 在特征维度上连结
            x = torch.cat((context, torch.unsqueeze(x, dim=1)), dim=-1)
            # 将x变形为(1,batch_size,embed_size+num_hiddens)
            out, hidden_state = self.rnn(x.permute(1, 0, 2), hidden_state)
            outputs.append(out)
            self._attention_weights.append(self.attention.attention_weights)
        # 全连接层变换后，outputs的形状为
        # (num_steps,batch_size,vocab_size)
        outputs = self.dense(torch.cat(outputs, dim=0))
        return outputs.permute(1, 0, 2), [enc_outputs, hidden_state,
                                          enc_valid_lens]

    @property
    def attention_weights(self):
        return self._attention_weights

embed_size, num_hiddens, num_layers, dropout = 32, 32, 2, 0.1
batch_size, num_steps = 64, 10
lr, num_epochs, device = 0.005, 250, d2l.try_gpu()
# 训练
train_iter, src_vocab, tgt_vocab = d2l.load_data_nmt(batch_size, num_steps)
encoder = d2l.Seq2SeqEncoder(
    len(src_vocab), embed_size, num_hiddens, num_layers, dropout)
decoder = Seq2SeqAttentionDecoder(
    len(tgt_vocab), embed_size, num_hiddens, num_layers, dropout)
net = d2l.EncoderDecoder(encoder, decoder)
d2l.train_seq2seq(net, train_iter, lr, num_epochs, tgt_vocab, device)
# loss 0.021, 5827.9 tokens/sec on cuda:0

# 翻译测试并计算BLEU分数
engs = ['go .', "i lost .", 'he\'s calm .', 'i\'m home .']
fras = ['va !', 'j\'ai perdu .', 'il est calme .', 'je suis chez moi .']
for eng, fra in zip(engs, fras):
    translation, dec_attention_weight_seq = d2l.predict_seq2seq(
        net, eng, src_vocab, tgt_vocab, num_steps, device, True)
    print(f'{eng} => {translation}, ',
          f'bleu {d2l.bleu(translation, fra, k=2):.3f}')

attention_weights = torch.cat([step[0][0][0] for step in dec_attention_weight_seq], 0).reshape((
    1, 1, -1, num_steps))
# 可视化注意力权重
d2l.show_heatmaps(
    attention_weights[:, :, :, :len(engs[-1].split()) + 1].cpu(),
    xlabel='Key positions', ylabel='Query positions')

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

#@save
def transpose_qkv(X, num_heads):
    """为了多注意力头的并行计算而变换形状"""
    # 输入X的形状:(batch_size，查询或者“键－值”对的个数，num_hiddens)
    # 输出X的形状:(batch_size，查询或者“键－值”对的个数，num_heads，
    # num_hiddens/num_heads)
    X = X.reshape(X.shape[0], X.shape[1], num_heads, -1)

    # 输出X的形状:(batch_size，num_heads，查询或者“键－值”对的个数,
    # num_hiddens/num_heads)
    X = X.permute(0, 2, 1, 3)

    # 最终输出的形状:(batch_size*num_heads,查询或者“键－值”对的个数,
    # num_hiddens/num_heads)
    return X.reshape(-1, X.shape[2], X.shape[3])

#@save
def transpose_output(X, num_heads):
    """逆转transpose_qkv函数的操作"""
    X = X.reshape(-1, num_heads, X.shape[1], X.shape[2])
    X = X.permute(0, 2, 1, 3)
    return X.reshape(X.shape[0], X.shape[1], -1)

#@save
class MultiHeadAttention(nn.Module):
    """多头注意力"""
    def __init__(self, key_size, query_size, value_size, num_hiddens,
                 num_heads, dropout, bias=False, **kwargs):
        super(MultiHeadAttention, self).__init__(**kwargs)
        self.num_heads = num_heads
        self.attention = d2l.DotProductAttention(dropout)
        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)

#@save
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)

# 位置编码可视化
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)])

import math
import pandas as pd
import torch
from torch import nn
from d2l import torch as d2l

#@save
class PositionWiseFFN(nn.Module):
    """基于位置的前馈网络"""
    def __init__(self, ffn_num_input, ffn_num_hiddens, ffn_num_outputs,
                 **kwargs):
        super(PositionWiseFFN, self).__init__(**kwargs)
        self.dense1 = nn.Linear(ffn_num_input, ffn_num_hiddens)
        self.relu = nn.ReLU()
        self.dense2 = nn.Linear(ffn_num_hiddens, ffn_num_outputs)

    def forward(self, X):
        return self.dense2(self.relu(self.dense1(X)))

#@save
class AddNorm(nn.Module):
    """残差连接后进行层归一化"""
    def __init__(self, normalized_shape, dropout, **kwargs):
        super(AddNorm, self).__init__(**kwargs)
        self.dropout = nn.Dropout(dropout)
        self.ln = nn.LayerNorm(normalized_shape)

    def forward(self, X, Y):
        return self.ln(self.dropout(Y) + X)

#@save
class EncoderBlock(nn.Module):
    """transformer编码器块"""
    def __init__(self, key_size, query_size, value_size, num_hiddens,
                 norm_shape, ffn_num_input, ffn_num_hiddens, num_heads,
                 dropout, use_bias=False, **kwargs):
        super(EncoderBlock, self).__init__(**kwargs)
        self.attention = d2l.MultiHeadAttention(
            key_size, query_size, value_size, num_hiddens, num_heads, dropout,
            use_bias)
        self.addnorm1 = AddNorm(norm_shape, dropout)
        self.ffn = PositionWiseFFN(
            ffn_num_input, ffn_num_hiddens, num_hiddens)
        self.addnorm2 = AddNorm(norm_shape, dropout)

    def forward(self, X, valid_lens): # 自注意力
        Y = self.addnorm1(X, self.attention(X, X, X, valid_lens))
        return self.addnorm2(Y, self.ffn(Y))
#@save
class TransformerEncoder(d2l.Encoder):
    """transformer编码器"""
    def __init__(self, vocab_size, key_size, query_size, value_size,
                 num_hiddens, norm_shape, ffn_num_input, ffn_num_hiddens,
                 num_heads, num_layers, dropout, use_bias=False, **kwargs):
        super(TransformerEncoder, self).__init__(**kwargs)
        self.num_hiddens = num_hiddens
        self.embedding = nn.Embedding(vocab_size, num_hiddens)
        self.pos_encoding = d2l.PositionalEncoding(num_hiddens, dropout)
        self.blks = nn.Sequential()
        for i in range(num_layers):
            self.blks.add_module("block"+str(i),
                EncoderBlock(key_size, query_size, value_size, num_hiddens,
                             norm_shape, ffn_num_input, ffn_num_hiddens,
                             num_heads, dropout, use_bias))

    def forward(self, X, valid_lens, *args):
        # 因为位置编码值在-1和1之间，
        # 因此嵌入值乘以嵌入维度的平方根进行缩放，
        # 然后再与位置编码相加。
        X = self.pos_encoding(self.embedding(X) * math.sqrt(self.num_hiddens))
        self.attention_weights = [None] * len(self.blks)
        for i, blk in enumerate(self.blks):
            X = blk(X, valid_lens)
            self.attention_weights[
                i] = blk.attention.attention.attention_weights
        return X

class DecoderBlock(nn.Module):
    """解码器中第i个块"""
    def __init__(self, key_size, query_size, value_size, num_hiddens,
                 norm_shape, ffn_num_input, ffn_num_hiddens, num_heads,
                 dropout, i, **kwargs):
        super(DecoderBlock, self).__init__(**kwargs)
        self.i = i
        self.attention1 = d2l.MultiHeadAttention(
            key_size, query_size, value_size, num_hiddens, num_heads, dropout)
        self.addnorm1 = AddNorm(norm_shape, dropout)
        self.attention2 = d2l.MultiHeadAttention(
            key_size, query_size, value_size, num_hiddens, num_heads, dropout)
        self.addnorm2 = AddNorm(norm_shape, dropout)
        self.ffn = PositionWiseFFN(ffn_num_input, ffn_num_hiddens,
                                   num_hiddens)
        self.addnorm3 = AddNorm(norm_shape, dropout)

    def forward(self, X, state):
        enc_outputs, enc_valid_lens = state[0], state[1]
        # 训练阶段，输出序列的所有词元都在同一时间处理，
        # 因此state[2][self.i]初始化为None。
        # 预测阶段，输出序列是通过词元一个接着一个解码的，
        # 因此state[2][self.i]包含着直到当前时间步第i个块解码的输出表示
        if state[2][self.i] is None:
            key_values = X
        else:
            key_values = torch.cat((state[2][self.i], X), axis=1)
        state[2][self.i] = key_values
        if self.training:
            batch_size, num_steps, _ = X.shape
            # dec_valid_lens的开头:(batch_size,num_steps),
            # 其中每一行是[1,2,...,num_steps]
            dec_valid_lens = torch.arange(
                1, num_steps + 1, device=X.device).repeat(batch_size, 1)
        else:
            dec_valid_lens = None

        # 带掩码的多头自注意力
        X2 = self.attention1(X, key_values, key_values, dec_valid_lens)
        Y = self.addnorm1(X, X2)
        # 编码器－解码器注意力 cross-attention
        # enc_outputs的开头:(batch_size,num_steps,num_hiddens)
        Y2 = self.attention2(Y, enc_outputs, enc_outputs, enc_valid_lens)
        Z = self.addnorm2(Y, Y2)
        return self.addnorm3(Z, self.ffn(Z)), state

class TransformerDecoder(d2l.AttentionDecoder):
    """transformer解码器"""
    def __init__(self, vocab_size, key_size, query_size, value_size,
                 num_hiddens, norm_shape, ffn_num_input, ffn_num_hiddens,
                 num_heads, num_layers, dropout, **kwargs):
        super(TransformerDecoder, self).__init__(**kwargs)
        self.num_hiddens = num_hiddens
        self.num_layers = num_layers
        self.embedding = nn.Embedding(vocab_size, num_hiddens)
        self.pos_encoding = d2l.PositionalEncoding(num_hiddens, dropout)
        self.blks = nn.Sequential()
        for i in range(num_layers):
            self.blks.add_module("block"+str(i),
                DecoderBlock(key_size, query_size, value_size, num_hiddens,
                             norm_shape, ffn_num_input, ffn_num_hiddens,
                             num_heads, dropout, i))
        self.dense = nn.Linear(num_hiddens, vocab_size)

    def init_state(self, enc_outputs, enc_valid_lens, *args):
        return [enc_outputs, enc_valid_lens, [None] * self.num_layers]

    def forward(self, X, state):
        X = self.pos_encoding(self.embedding(X) * math.sqrt(self.num_hiddens))
        self._attention_weights = [[None] * len(self.blks) for _ in range (2)]
        for i, blk in enumerate(self.blks):
            X, state = blk(X, state)
            # 解码器自注意力权重
            self._attention_weights[0][
                i] = blk.attention1.attention.attention_weights
            # “编码器－解码器”自注意力权重
            self._attention_weights[1][
                i] = blk.attention2.attention.attention_weights
        return self.dense(X), state

    @property
    def attention_weights(self):
        return self._attention_weights

# 训练
num_hiddens, num_layers, dropout, batch_size, num_steps = 32, 2, 0.1, 64, 10
lr, num_epochs, device = 0.005, 200, d2l.try_gpu()
ffn_num_input, ffn_num_hiddens, num_heads = 32, 64, 4
key_size, query_size, value_size = 32, 32, 32
norm_shape = [32]

train_iter, src_vocab, tgt_vocab = d2l.load_data_nmt(batch_size, num_steps)

encoder = TransformerEncoder(
    len(src_vocab), key_size, query_size, value_size, num_hiddens,
    norm_shape, ffn_num_input, ffn_num_hiddens, num_heads,
    num_layers, dropout)
decoder = TransformerDecoder(
    len(tgt_vocab), key_size, query_size, value_size, num_hiddens,
    norm_shape, ffn_num_input, ffn_num_hiddens, num_heads,
    num_layers, dropout)
net = d2l.EncoderDecoder(encoder, decoder)
d2l.train_seq2seq(net, train_iter, lr, num_epochs, tgt_vocab, device)
# loss 0.033, 5849.7 tokens/sec on cuda:0

# 预测与BLEU分数计算
engs = ['go .', "i lost .", 'he\'s calm .', 'i\'m home .']
fras = ['va !', 'j\'ai perdu .', 'il est calme .', 'je suis chez moi .']
for eng, fra in zip(engs, fras):
    translation, dec_attention_weight_seq = d2l.predict_seq2seq(
        net, eng, src_vocab, tgt_vocab, num_steps, device, True)
    print(f'{eng} => {translation}, ',
          f'bleu {d2l.bleu(translation, fra, k=2):.3f}')
# go . => va !,  bleu 1.000
# i lost . => je vous en prie .,  bleu 0.000
# he's calm . => il est calme .,  bleu 1.000
# i'm home . => je suis chez moi .,  bleu 1.000

# 编码器多头自注意力可视化
enc_attention_weights = torch.cat(net.encoder.attention_weights, 0).reshape((num_layers, num_heads,
    -1, num_steps))
d2l.show_heatmaps(
    enc_attention_weights.cpu(), xlabel='Key positions',
    ylabel='Query positions', titles=['Head %d' % i for i in range(1, 5)],
    figsize=(7, 3.5))

# 数据预处理
dec_attention_weights_2d = [head[0].tolist()
                            for step in dec_attention_weight_seq
                            for attn in step for blk in attn for head in blk]
dec_attention_weights_filled = torch.tensor(
    pd.DataFrame(dec_attention_weights_2d).fillna(0.0).values)
dec_attention_weights = dec_attention_weights_filled.reshape((-1, 2, num_layers, num_heads, num_steps))
dec_self_attention_weights, dec_inter_attention_weights = \
    dec_attention_weights.permute(1, 2, 3, 0, 4)
dec_self_attention_weights.shape, dec_inter_attention_weights.shape

# Plusonetoincludethebeginning-of-sequencetoken
# 解码器多头self-attention可视化
d2l.show_heatmaps(
    dec_self_attention_weights[:, :, :, :len(translation.split()) + 1],
    xlabel='Key positions', ylabel='Query positions',
    titles=['Head %d' % i for i in range(1, 5)], figsize=(7, 3.5))

# 解码器多头cross-attention可视化
d2l.show_heatmaps(
    dec_inter_attention_weights, xlabel='Key positions',
    ylabel='Query positions', titles=['Head %d' % i for i in range(1, 5)],
    figsize=(7, 3.5))

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

# 构建子图的嵌入表示
class PatchEmbedding(nn.Module):
    def __init__(self, img_size=96, patch_size=16, num_hiddens=512):
        super().__init__()
        def _make_tuple(x):
            if not isinstance(x, (list, tuple)):
                return (x, x)
            return x
        img_size, patch_size = _make_tuple(img_size), _make_tuple(patch_size)
        self.num_patches = (img_size[0] // patch_size[0]) * (
            img_size[1] // patch_size[1])
        self.conv = nn.LazyConv2d(num_hiddens, kernel_size=patch_size,
                                  stride=patch_size)

    def forward(self, X):
        # Output shape: (batch size, no. of patches, no. of channels)
        return self.conv(X).flatten(2).transpose(1, 2)

# MLP使用dropout进行正则化，使用GELU作为激活函数
class ViTMLP(nn.Module):
    def __init__(self, mlp_num_hiddens, mlp_num_outputs, dropout=0.5):
        super().__init__()
        self.dense1 = nn.LazyLinear(mlp_num_hiddens)
        self.gelu = nn.GELU()
        self.dropout1 = nn.Dropout(dropout)
        self.dense2 = nn.LazyLinear(mlp_num_outputs)
        self.dropout2 = nn.Dropout(dropout)

    def forward(self, x):
        return self.dropout2(self.dense2(self.dropout1(self.gelu(
            self.dense1(x)))))

# 多头注意力和MLP构成ViT块
class ViTBlock(nn.Module):
    def __init__(self, num_hiddens, norm_shape, mlp_num_hiddens,
                 num_heads, dropout, use_bias=False):
        super().__init__()
        self.ln1 = nn.LayerNorm(norm_shape)
        self.attention = d2l.MultiHeadAttention(num_hiddens, num_heads,
                                                dropout, use_bias)
        self.ln2 = nn.LayerNorm(norm_shape)
        self.mlp = ViTMLP(mlp_num_hiddens, num_hiddens, dropout)

    def forward(self, X, valid_lens=None):
        X = self.ln1(X)
        return X + self.mlp(self.ln2(
            X + self.attention(X, X, X, valid_lens)))

# ViTs模型整体结构
class ViT(d2l.Classifier):
    """Vision transformer."""
    def __init__(self, img_size, patch_size, num_hiddens, mlp_num_hiddens,
                 num_heads, num_blks, emb_dropout, blk_dropout, lr=0.1,
                 use_bias=False, num_classes=10):
        super().__init__()
        self.save_hyperparameters()
        self.patch_embedding = PatchEmbedding(
            img_size, patch_size, num_hiddens)
        self.cls_token = nn.Parameter(torch.zeros(1, 1, num_hiddens))
        num_steps = self.patch_embedding.num_patches + 1  # Add the cls token
        # Positional embeddings are learnable
        self.pos_embedding = nn.Parameter(
            torch.randn(1, num_steps, num_hiddens))
        self.dropout = nn.Dropout(emb_dropout)
        self.blks = nn.Sequential()
        for i in range(num_blks):
            self.blks.add_module(f"{i}", ViTBlock(
                num_hiddens, num_hiddens, mlp_num_hiddens,
                num_heads, blk_dropout, use_bias))
        self.head = nn.Sequential(nn.LayerNorm(num_hiddens),
                                  nn.Linear(num_hiddens, num_classes))

    def forward(self, X):
        X = self.patch_embedding(X)
        X = torch.cat((self.cls_token.expand(X.shape[0], -1, -1), X), 1)
        X = self.dropout(X + self.pos_embedding)
        for blk in self.blks:
            X = blk(X)
        return self.head(X[:, 0])

# 模型训练
img_size, patch_size = 96, 16
num_hiddens, mlp_num_hiddens, num_heads, num_blks = 512, 2048, 8, 2
emb_dropout, blk_dropout, lr = 0.1, 0.1, 0.1
model = ViT(img_size, patch_size, num_hiddens, mlp_num_hiddens, num_heads,
            num_blks, emb_dropout, blk_dropout, lr)
trainer = d2l.Trainer(max_epochs=10, num_gpus=1)
data = d2l.FashionMNIST(batch_size=128, resize=(img_size, img_size))
trainer.fit(model, data)