File size: 9,229 Bytes
8cb4f3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
import torch.nn as nn
from torchtext import data
import copy
import layers as layers

class Embedder(nn.Module):
   def __init__(self, vocab_size, d_model):
       super().__init__()
       self.vocab_size = vocab_size
       self.d_model = d_model
       
       self.embed = nn.Embedding(vocab_size, d_model)
       
   def forward(self, x):
       return self.embed(x)

class EncoderLayer(nn.Module):
    def __init__(self, d_model, heads, dropout=0.1):
        """An layer of the encoder. Contain a self-attention accepting padding mask
        Args:
            d_model: the inner dimension size of the layer
            heads: number of heads used in the attention
            dropout: applied dropout value during training
            """
        super().__init__()
        self.norm_1 = layers.Norm(d_model)
        self.norm_2 = layers.Norm(d_model)
        self.attn = layers.MultiHeadAttention(heads, d_model, dropout=dropout)
        self.ff = layers.FeedForward(d_model, dropout=dropout)
        self.dropout_1 = nn.Dropout(dropout)
        self.dropout_2 = nn.Dropout(dropout)

    def forward(self, x, src_mask):
        """Run the encoding layer
        Args:
            x: the input (either embedding values or previous layer output), should be in shape [batch_size, src_len, d_model]
            src_mask: the padding mask, should be [batch_size, 1, src_len]
        Return:
            an output that have the same shape as input, [batch_size, src_len, d_model]
            the attention used [batch_size, src_len, src_len]
        """
        x2 = self.norm_1(x)
        # Self attention only
        x_sa, sa = self.attn(x2, x2, x2, src_mask)
        x = x + self.dropout_1(x_sa)
        x2 = self.norm_2(x)
        x = x + self.dropout_2(self.ff(x2))
        return x, sa

class DecoderLayer(nn.Module):
    def __init__(self, d_model, heads, dropout=0.1):
        """An layer of the decoder. Contain a self-attention that accept no-peeking mask and a normal attention tha t accept padding mask
        Args:
            d_model: the inner dimension size of the layer
            heads: number of heads used in the attention
            dropout: applied dropout value during training
            """
        super().__init__()
        self.norm_1 = layers.Norm(d_model)
        self.norm_2 = layers.Norm(d_model)
        self.norm_3 = layers.Norm(d_model)

        self.dropout_1 = nn.Dropout(dropout)
        self.dropout_2 = nn.Dropout(dropout)
        self.dropout_3 = nn.Dropout(dropout)

        self.attn_1 = layers.MultiHeadAttention(heads, d_model, dropout=dropout)
        self.attn_2 = layers.MultiHeadAttention(heads, d_model, dropout=dropout)
        self.ff = layers.FeedForward(d_model, dropout=dropout)

    def forward(self, x, memory, src_mask, trg_mask):
        """Run the decoding layer
        Args:
            x: the input (either embedding values or previous layer output), should be in shape [batch_size, tgt_len, d_model]
            memory: the outputs of the encoding section, used for normal attention. [batch_size, src_len, d_model]
            src_mask: the padding mask for the memory, [batch_size, 1, src_len]
            tgt_mask: the no-peeking mask for the decoder, [batch_size, tgt_len, tgt_len]
        Return:
            an output that have the same shape as input, [batch_size, tgt_len, d_model]
            the self-attention and normal attention received [batch_size, head, tgt_len, tgt_len] & [batch_size, head, tgt_len, src_len]
        """
        x2 = self.norm_1(x)
        # Self-attention
        x_sa, sa = self.attn_1(x2, x2, x2, trg_mask)
        x = x + self.dropout_1(x_sa)
        x2 = self.norm_2(x)
        # Normal multi-head attention
        x_na, na = self.attn_2(x2, memory, memory, src_mask)
        x = x + self.dropout_2(x_na)
        x2 = self.norm_3(x)
        x = x + self.dropout_3(self.ff(x2))
        return x, (sa, na)

def get_clones(module, N, keep_module=True):
    if(keep_module and N >= 1):
        # create N-1 copies in addition to the original
        return nn.ModuleList([module] + [copy.deepcopy(module) for i in range(N-1)]) 
    else:
        # create N new copy
        return nn.ModuleList([copy.deepcopy(module) for i in range(N)])

class Encoder(nn.Module):
    """A wrapper that embed, positional encode, and self-attention encode the inputs.
    Args:
        vocab_size: the size of the vocab. Used for embedding
        d_model: the inner dim of the module
        N: number of layers used
        heads: number of heads used in the attention
        dropout: applied dropout value during training
        max_seq_length: the maximum length value used for this encoder. Needed for PositionalEncoder, due to caching
    """
    def __init__(self, vocab_size, d_model, N, heads, dropout, max_seq_length=200):
        super().__init__()
        self.N = N
        self.embed = nn.Embedding(vocab_size, d_model)
        self.pe = layers.PositionalEncoder(d_model, dropout=dropout, max_seq_length=max_seq_length)
        self.layers = get_clones(EncoderLayer(d_model, heads, dropout), N)
        self.norm = layers.Norm(d_model)

        self._max_seq_length = max_seq_length

    def forward(self, src, src_mask, output_attention=False, seq_length_check=False):
        """Accepts a batch of indexed tokens, return the encoded values.
        Args:
            src: int Tensor of [batch_size, src_len]
            src_mask: the padding mask, [batch_size, 1, src_len]
            output_attention: if set, output a list containing used attention
            seq_length_check: if set, automatically trim the input if it goes past the expected sequence length.
        Returns:
            the encoded values [batch_size, src_len, d_model]
            if available, list of N (self-attention) calculated. They are in form of [batch_size, heads, src_len, src_len]
        """
        if(seq_length_check and src.shape[1] > self._max_seq_length):
            src = src[:, :self._max_seq_length]
            src_mask = src_mask[:, :, :self._max_seq_length]
        x = self.embed(src)
        x = self.pe(x)
        attentions = [None] * self.N
        for i in range(self.N):
            x, attn = self.layers[i](x, src_mask)
            attentions[i] = attn
        x = self.norm(x)
        return x if(not output_attention) else (x, attentions)

class Decoder(nn.Module):
    """A wrapper that receive the encoder outputs, run through the decoder process for a determined input
    Args:
        vocab_size: the size of the vocab. Used for embedding
        d_model: the inner dim of the module
        N: number of layers used
        heads: number of heads used in the attention
        dropout: applied dropout value during training
        max_seq_length: the maximum length value used for this encoder. Needed for PositionalEncoder, due to caching
    """
    def __init__(self, vocab_size, d_model, N, heads, dropout, max_seq_length=200):
        super().__init__()
        self.N = N
        self.embed = nn.Embedding(vocab_size, d_model)
        self.pe = layers.PositionalEncoder(d_model, dropout=dropout, max_seq_length=max_seq_length)
        self.layers = get_clones(DecoderLayer(d_model, heads, dropout), N)
        self.norm = layers.Norm(d_model)

        self._max_seq_length = max_seq_length

    def forward(self, trg, memory, src_mask, trg_mask, output_attention=False):
        """Accepts a batch of indexed tokens and the encoding outputs, return the decoded values.
        Args:
            trg: input Tensor of [batch_size, trg_len]
            memory: output of Encoder [batch_size, src_len, d_model]
            src_mask: the padding mask, [batch_size, 1, src_len]
            trg_mask: the no-peeking mask, [batch_size, tgt_len, tgt_len]
            output_attention: if set, output a list containing used attention
        Returns:
            the decoded values [batch_size, tgt_len, d_model]
            if available, list of N (self-attention, attention) calculated. They are in form of [batch_size, heads, tgt_len, tgt/src_len]
        """
        x = self.embed(trg)
        x = self.pe(x)

        attentions = [None] * self.N
        for i in range(self.N):
            x, attn = self.layers[i](x, memory, src_mask, trg_mask)
            attentions[i] = attn
        x = self.norm(x)
        return x if(not output_attention) else (x, attentions)


class Config:
    """Deprecated"""
    def __init__(self):
        self.opt = {
            'train_src_data':'/workspace/khoai23/opennmt/data/iwslt_en_vi/train.en',
            'train_trg_data':'/workspace/khoai23/opennmt/data/iwslt_en_vi/train.vi',
            'valid_src_data':'/workspace/khoai23/opennmt/data/iwslt_en_vi/tst2013.en',
            'valid_trg_data':'/workspace/khoai23/opennmt/data/iwslt_en_vi/tst2013.vi',
            'src_lang':'en', # useless atm
            'trg_lang':'en',#'vi_spacy_model', # useless atm
            'max_strlen':160,
            'batchsize':1500,
            'device':'cuda',
            'd_model': 512,
            'n_layers': 6,
            'heads': 8,
            'dropout': 0.1,
            'lr':0.0001,
            'epochs':30,
            'printevery': 200,
            'k':5,
        }