File size: 11,634 Bytes
0667c13 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 |
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
class Encoder(nn.Module):
def __init__(self,
emb_dim,
hid_dim,
n_layers,
kernel_size,
dropout,
device,
max_length = 512):
super().__init__()
assert kernel_size % 2 == 1, "Kernel size must be odd!"
self.device = device
self.scale = torch.sqrt(torch.FloatTensor([0.5])).to(device)
# self.tok_embedding = nn.Embedding(input_dim, emb_dim)
self.pos_embedding = nn.Embedding(max_length, emb_dim)
self.emb2hid = nn.Linear(emb_dim, hid_dim)
self.hid2emb = nn.Linear(hid_dim, emb_dim)
self.convs = nn.ModuleList([nn.Conv1d(in_channels = hid_dim,
out_channels = 2 * hid_dim,
kernel_size = kernel_size,
padding = (kernel_size - 1) // 2)
for _ in range(n_layers)])
self.dropout = nn.Dropout(dropout)
def forward(self, src):
#src = [batch size, src len]
src = src.transpose(0, 1)
batch_size = src.shape[0]
src_len = src.shape[1]
device = src.device
#create position tensor
pos = torch.arange(0, src_len).unsqueeze(0).repeat(batch_size, 1).to(device)
#pos = [0, 1, 2, 3, ..., src len - 1]
#pos = [batch size, src len]
#embed tokens and positions
# tok_embedded = self.tok_embedding(src)
tok_embedded = src
pos_embedded = self.pos_embedding(pos)
#tok_embedded = pos_embedded = [batch size, src len, emb dim]
#combine embeddings by elementwise summing
embedded = self.dropout(tok_embedded + pos_embedded)
#embedded = [batch size, src len, emb dim]
#pass embedded through linear layer to convert from emb dim to hid dim
conv_input = self.emb2hid(embedded)
#conv_input = [batch size, src len, hid dim]
#permute for convolutional layer
conv_input = conv_input.permute(0, 2, 1)
#conv_input = [batch size, hid dim, src len]
#begin convolutional blocks...
for i, conv in enumerate(self.convs):
#pass through convolutional layer
conved = conv(self.dropout(conv_input))
#conved = [batch size, 2 * hid dim, src len]
#pass through GLU activation function
conved = F.glu(conved, dim = 1)
#conved = [batch size, hid dim, src len]
#apply residual connection
conved = (conved + conv_input) * self.scale
#conved = [batch size, hid dim, src len]
#set conv_input to conved for next loop iteration
conv_input = conved
#...end convolutional blocks
#permute and convert back to emb dim
conved = self.hid2emb(conved.permute(0, 2, 1))
#conved = [batch size, src len, emb dim]
#elementwise sum output (conved) and input (embedded) to be used for attention
combined = (conved + embedded) * self.scale
#combined = [batch size, src len, emb dim]
return conved, combined
class Decoder(nn.Module):
def __init__(self,
output_dim,
emb_dim,
hid_dim,
n_layers,
kernel_size,
dropout,
trg_pad_idx,
device,
max_length = 512):
super().__init__()
self.kernel_size = kernel_size
self.trg_pad_idx = trg_pad_idx
self.device = device
self.scale = torch.sqrt(torch.FloatTensor([0.5])).to(device)
self.tok_embedding = nn.Embedding(output_dim, emb_dim)
self.pos_embedding = nn.Embedding(max_length, emb_dim)
self.emb2hid = nn.Linear(emb_dim, hid_dim)
self.hid2emb = nn.Linear(hid_dim, emb_dim)
self.attn_hid2emb = nn.Linear(hid_dim, emb_dim)
self.attn_emb2hid = nn.Linear(emb_dim, hid_dim)
self.fc_out = nn.Linear(emb_dim, output_dim)
self.convs = nn.ModuleList([nn.Conv1d(in_channels = hid_dim,
out_channels = 2 * hid_dim,
kernel_size = kernel_size)
for _ in range(n_layers)])
self.dropout = nn.Dropout(dropout)
def calculate_attention(self, embedded, conved, encoder_conved, encoder_combined):
#embedded = [batch size, trg len, emb dim]
#conved = [batch size, hid dim, trg len]
#encoder_conved = encoder_combined = [batch size, src len, emb dim]
#permute and convert back to emb dim
conved_emb = self.attn_hid2emb(conved.permute(0, 2, 1))
#conved_emb = [batch size, trg len, emb dim]
combined = (conved_emb + embedded) * self.scale
#combined = [batch size, trg len, emb dim]
energy = torch.matmul(combined, encoder_conved.permute(0, 2, 1))
#energy = [batch size, trg len, src len]
attention = F.softmax(energy, dim=2)
#attention = [batch size, trg len, src len]
attended_encoding = torch.matmul(attention, encoder_combined)
#attended_encoding = [batch size, trg len, emd dim]
#convert from emb dim -> hid dim
attended_encoding = self.attn_emb2hid(attended_encoding)
#attended_encoding = [batch size, trg len, hid dim]
#apply residual connection
attended_combined = (conved + attended_encoding.permute(0, 2, 1)) * self.scale
#attended_combined = [batch size, hid dim, trg len]
return attention, attended_combined
def forward(self, trg, encoder_conved, encoder_combined):
#trg = [batch size, trg len]
#encoder_conved = encoder_combined = [batch size, src len, emb dim]
trg = trg.transpose(0, 1)
batch_size = trg.shape[0]
trg_len = trg.shape[1]
device = trg.device
#create position tensor
pos = torch.arange(0, trg_len).unsqueeze(0).repeat(batch_size, 1).to(device)
#pos = [batch size, trg len]
#embed tokens and positions
tok_embedded = self.tok_embedding(trg)
pos_embedded = self.pos_embedding(pos)
#tok_embedded = [batch size, trg len, emb dim]
#pos_embedded = [batch size, trg len, emb dim]
#combine embeddings by elementwise summing
embedded = self.dropout(tok_embedded + pos_embedded)
#embedded = [batch size, trg len, emb dim]
#pass embedded through linear layer to go through emb dim -> hid dim
conv_input = self.emb2hid(embedded)
#conv_input = [batch size, trg len, hid dim]
#permute for convolutional layer
conv_input = conv_input.permute(0, 2, 1)
#conv_input = [batch size, hid dim, trg len]
batch_size = conv_input.shape[0]
hid_dim = conv_input.shape[1]
for i, conv in enumerate(self.convs):
#apply dropout
conv_input = self.dropout(conv_input)
#need to pad so decoder can't "cheat"
padding = torch.zeros(batch_size,
hid_dim,
self.kernel_size - 1).fill_(self.trg_pad_idx).to(device)
padded_conv_input = torch.cat((padding, conv_input), dim = 2)
#padded_conv_input = [batch size, hid dim, trg len + kernel size - 1]
#pass through convolutional layer
conved = conv(padded_conv_input)
#conved = [batch size, 2 * hid dim, trg len]
#pass through GLU activation function
conved = F.glu(conved, dim = 1)
#conved = [batch size, hid dim, trg len]
#calculate attention
attention, conved = self.calculate_attention(embedded,
conved,
encoder_conved,
encoder_combined)
#attention = [batch size, trg len, src len]
#apply residual connection
conved = (conved + conv_input) * self.scale
#conved = [batch size, hid dim, trg len]
#set conv_input to conved for next loop iteration
conv_input = conved
conved = self.hid2emb(conved.permute(0, 2, 1))
#conved = [batch size, trg len, emb dim]
output = self.fc_out(self.dropout(conved))
#output = [batch size, trg len, output dim]
return output, attention
class ConvSeq2Seq(nn.Module):
def __init__(self, vocab_size, emb_dim, hid_dim, enc_layers, dec_layers, enc_kernel_size, dec_kernel_size, enc_max_length, dec_max_length, dropout, pad_idx, device):
super().__init__()
enc = Encoder(emb_dim, hid_dim, enc_layers, enc_kernel_size, dropout, device, enc_max_length)
dec = Decoder(vocab_size, emb_dim, hid_dim, dec_layers, dec_kernel_size, dropout, pad_idx, device, dec_max_length)
self.encoder = enc
self.decoder = dec
def forward_encoder(self, src):
encoder_conved, encoder_combined = self.encoder(src)
return encoder_conved, encoder_combined
def forward_decoder(self, trg, memory):
encoder_conved, encoder_combined = memory
output, attention = self.decoder(trg, encoder_conved, encoder_combined)
return output, (encoder_conved, encoder_combined)
def forward(self, src, trg):
#src = [batch size, src len]
#trg = [batch size, trg len - 1] (<eos> token sliced off the end)
#calculate z^u (encoder_conved) and (z^u + e) (encoder_combined)
#encoder_conved is output from final encoder conv. block
#encoder_combined is encoder_conved plus (elementwise) src embedding plus
# positional embeddings
encoder_conved, encoder_combined = self.encoder(src)
#encoder_conved = [batch size, src len, emb dim]
#encoder_combined = [batch size, src len, emb dim]
#calculate predictions of next words
#output is a batch of predictions for each word in the trg sentence
#attention a batch of attention scores across the src sentence for
# each word in the trg sentence
output, attention = self.decoder(trg, encoder_conved, encoder_combined)
#output = [batch size, trg len - 1, output dim]
#attention = [batch size, trg len - 1, src len]
return output#, attention
|