-
Notifications
You must be signed in to change notification settings - Fork 0
/
train.py
240 lines (192 loc) · 10.2 KB
/
train.py
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
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
import time
from transformer_sample.SlitherTransformer import utils
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import math
## 10
def get_attn_subsequent_mask(seq):
"""
seq: [batch_size, tgt_len]
"""
attn_shape = [seq.size(0), seq.size(1), seq.size(1)]
# attn_shape: [batch_size, tgt_len, tgt_len]
subsequence_mask = np.triu(np.ones(attn_shape), k=1) # 生成一个上三角矩阵
subsequence_mask = torch.from_numpy(subsequence_mask).byte()
return subsequence_mask # [batch_size, tgt_len, tgt_len]
## 7. ScaledDotProductAttention
class ScaledDotProductAttention(nn.Module):
def __init__(self):
super(ScaledDotProductAttention, self).__init__()
def forward(self, Q, K, V, attn_mask):
## 输入进来的维度分别是 [batch_size x n_heads x len_q x d_k] K: [batch_size x n_heads x len_k x d_k] V: [batch_size x n_heads x len_k x d_v]
##首先经过matmul函数得到的scores形状是 : [batch_size x n_heads x len_q x len_k]
scores = torch.matmul(Q, K.transpose(-1, -2)) / np.sqrt(d_k)
## 然后关键词地方来了,下面这个就是用到了我们之前重点讲的attn_mask,把被mask的地方置为无限小,softmax之后基本就是0,对q的单词不起作用
scores.masked_fill_(attn_mask, -1e9) # Fills elements of self tensor with value where mask is one.
attn = nn.Softmax(dim=-1)(scores)
context = torch.matmul(attn, V)
return context, attn
## 6. MultiHeadAttention
class MultiHeadAttention(nn.Module):
def __init__(self):
super(MultiHeadAttention, self).__init__()
## 输入进来的QKV是相等的,我们会使用映射linear做一个映射得到参数矩阵Wq, Wk,Wv
self.W_Q = nn.Linear(d_model, d_k * n_heads)
self.W_K = nn.Linear(d_model, d_k * n_heads)
self.W_V = nn.Linear(d_model, d_v * n_heads)
self.linear = nn.Linear(n_heads * d_v, d_model)
self.layer_norm = nn.LayerNorm(d_model)
def forward(self, Q, K, V, attn_mask):
residual, batch_size = Q, Q.size(0)
q_s = self.W_Q(Q).view(batch_size, -1, n_heads, d_k).transpose(1,2) # q_s: [batch_size x n_heads x len_q x d_k]
k_s = self.W_K(K).view(batch_size, -1, n_heads, d_k).transpose(1,2) # k_s: [batch_size x n_heads x len_k x d_k]
v_s = self.W_V(V).view(batch_size, -1, n_heads, d_v).transpose(1,2) # v_s: [batch_size x n_heads x len_k x d_v]
attn_mask = attn_mask.unsqueeze(1).repeat(1, n_heads, 1, 1)
context, attn = ScaledDotProductAttention()(q_s, k_s, v_s, attn_mask)
context = context.transpose(1, 2).contiguous().view(batch_size, -1, n_heads * d_v) # context: [batch_size x len_q x n_heads * d_v]
output = self.linear(context)
return self.layer_norm(output + residual), attn # output: [batch_size x len_q x d_model]
## 8. PoswiseFeedForwardNet
class PoswiseFeedForwardNet(nn.Module):
def __init__(self):
super(PoswiseFeedForwardNet, self).__init__()
self.conv1 = nn.Conv1d(in_channels=d_model, out_channels=d_ff, kernel_size=1)
self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1)
self.layer_norm = nn.LayerNorm(d_model)
def forward(self, inputs):
residual = inputs # inputs : [batch_size, len_q, d_model]
output = nn.ReLU()(self.conv1(inputs.transpose(1, 2)))
output = self.conv2(output).transpose(1, 2)
return self.layer_norm(output + residual)
## 4. get_attn_pad_mask
def get_attn_pad_mask(seq_q, seq_k):
batch_size, len_q = seq_q.size()
batch_size, len_k = seq_k.size()
# eq(zero) is PAD token
pad_attn_mask = seq_k.data.eq(0).unsqueeze(1) # batch_size x 1 x len_k, one is masking
return pad_attn_mask.expand(batch_size, len_q, len_k) # batch_size x len_q x len_k
## 3. PositionalEncoding 代码实现
class PositionalEncoding(nn.Module):
def __init__(self, d_model, dropout=0.1, max_len=5000):
super(PositionalEncoding, self).__init__()
self.dropout = nn.Dropout(p=dropout)
pe = torch.zeros(max_len, d_model)
position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
pe[:, 0::2] = torch.sin(position * div_term)
pe[:, 1::2] = torch.cos(position * div_term)
pe = pe.unsqueeze(0).transpose(0, 1)
self.register_buffer('pe', pe)
def forward(self, x):
"""
x: [seq_len, batch_size, d_model]
"""
post = self.pe[:x.size(0), :]
x = x + self.pe[:x.size(0), :]
return self.dropout(x)
class EncoderLayer(nn.Module):
def __init__(self):
super(EncoderLayer, self).__init__()
self.enc_self_attn = MultiHeadAttention()
self.pos_ffn = PoswiseFeedForwardNet()
def forward(self, enc_inputs, enc_self_attn_mask):
enc_outputs, attn = self.enc_self_attn(enc_inputs, enc_inputs, enc_inputs, enc_self_attn_mask) # enc_inputs to same Q,K,V
enc_outputs = self.pos_ffn(enc_outputs) # enc_outputs: [batch_size x len_q x d_model]
return enc_outputs, attn
class Encoder(nn.Module):
def __init__(self):
super(Encoder, self).__init__()
self.src_emb = nn.Embedding(src_vocab_size, d_model)
self.pos_emb = PositionalEncoding(d_model)
self.layers = nn.ModuleList([EncoderLayer() for _ in range(n_layers)])
def forward(self, enc_inputs):
enc_outputs = self.src_emb(enc_inputs)
enc_outputs = self.pos_emb(enc_outputs.transpose(0, 1)).transpose(0, 1)
enc_self_attn_mask = get_attn_pad_mask(enc_inputs, enc_inputs)
enc_self_attns = []
for layer in self.layers:
enc_outputs, enc_self_attn = layer(enc_outputs, enc_self_attn_mask)
enc_self_attns.append(enc_self_attn)
return enc_outputs, enc_self_attns
# 10.
class DecoderLayer(nn.Module):
def __init__(self):
super(DecoderLayer, self).__init__()
self.dec_self_attn = MultiHeadAttention()
self.dec_enc_attn = MultiHeadAttention()
self.pos_ffn = PoswiseFeedForwardNet()
def forward(self, dec_inputs, enc_outputs, dec_self_attn_mask, dec_enc_attn_mask):
dec_outputs, dec_self_attn = self.dec_self_attn(dec_inputs, dec_inputs, dec_inputs, dec_self_attn_mask)
dec_outputs, dec_enc_attn = self.dec_enc_attn(dec_outputs, enc_outputs, enc_outputs, dec_enc_attn_mask)
dec_outputs = self.pos_ffn(dec_outputs)
return dec_outputs, dec_self_attn, dec_enc_attn
# 9. Decoder
class Decoder(nn.Module):
def __init__(self):
super(Decoder, self).__init__()
self.tgt_emb = nn.Embedding(tgt_vocab_size, d_model)
self.pos_emb = PositionalEncoding(d_model)
self.layers = nn.ModuleList([DecoderLayer() for _ in range(n_layers)])
def forward(self, dec_inputs, enc_inputs, enc_outputs): # dec_inputs : [batch_size x target_len]
dec_outputs = self.tgt_emb(dec_inputs) # [batch_size, tgt_len, d_model]
dec_outputs = self.pos_emb(dec_outputs.transpose(0, 1)).transpose(0, 1) # [batch_size, tgt_len, d_model]
dec_self_attn_pad_mask = get_attn_pad_mask(dec_inputs, dec_inputs)
dec_self_attn_pad_mask = dec_self_attn_pad_mask.cuda()
dec_self_attn_subsequent_mask = get_attn_subsequent_mask(dec_inputs)
dec_self_attn_subsequent_mask = dec_self_attn_subsequent_mask.cuda()
dec_self_attn_mask = torch.gt((dec_self_attn_pad_mask + dec_self_attn_subsequent_mask), 0)
dec_enc_attn_mask = get_attn_pad_mask(dec_inputs, enc_inputs)
dec_self_attns, dec_enc_attns = [], []
for layer in self.layers:
dec_outputs, dec_self_attn, dec_enc_attn = layer(dec_outputs, enc_outputs, dec_self_attn_mask, dec_enc_attn_mask)
dec_self_attns.append(dec_self_attn)
dec_enc_attns.append(dec_enc_attn)
return dec_outputs, dec_self_attns, dec_enc_attns
class Transformer(nn.Module):
def __init__(self):
super(Transformer, self).__init__()
self.encoder = Encoder()
self.decoder = Decoder()
self.projection = nn.Linear(d_model, tgt_vocab_size, bias=False)
def forward(self, enc_inputs, dec_inputs):
enc_outputs, enc_self_attns = self.encoder(enc_inputs)
dec_outputs, dec_self_attns, dec_enc_attns = self.decoder(dec_inputs, enc_inputs, enc_outputs)
dec_logits = self.projection(dec_outputs) # dec_logits : [batch_size x src_vocab_size x tgt_vocab_size]
return dec_logits.view(-1, dec_logits.size(-1)), enc_self_attns, dec_self_attns, dec_enc_attns
if __name__ == '__main__':
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
d_model = 512 # Embedding Size
d_ff = 2048 # FeedForward dimension
d_k = d_v = 64 # dimension of K(=Q), V
n_layers = 6 # number of Encoder of Decoder Layer
n_heads = 8 # number of heads in Multi-Head Attention
d = utils.DateData()
src_vocab_size = tgt_vocab_size = len(d.vocab)
model = Transformer()
model = model.to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.0001)
t0 = time.time()
for epoch in range(300):
optimizer.zero_grad()
enc_inputs,dec_inputs,target_batch = d.sample(200)
enc_inputs = enc_inputs.cuda()
dec_inputs = dec_inputs.cuda()
target_batch = target_batch.cuda()
outputs, enc_self_attns, dec_self_attns, dec_enc_attns = model(enc_inputs, dec_inputs) # enc_inputs(1,5)--dec_inputs(1,5)
loss = criterion(outputs, target_batch.contiguous().view(-1)).cuda()
loss.backward()
optimizer.step()
if epoch % 5 == 0 :
torch.save(model.state_dict(),"./transformer/model/model.pkl")
torch.save(optimizer.state_dict(),"./transformer/model/opt.pkl")
t1 = time.time()
print('Epoch:', '%04d' % (epoch + 1),
'| cost =', '{:.6f}'.format(loss),
"| time: %.2f" % (t1 - t0),
# "| target: ", "".join([d.i2v[i] for i in target_batch[0, 1:3]]),
# "| inference: ", "".join([d.i2v[i] for i in np.argmax(outputs, axis=1)[:2]]),
)
t0 = t1