-
Notifications
You must be signed in to change notification settings - Fork 2
/
modeling_caching.py
644 lines (550 loc) · 30.6 KB
/
modeling_caching.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
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
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""PyTorch BERT model. """
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import copy
import json
import math
import six
import torch
import torch.nn as nn
from torch.nn import CrossEntropyLoss
torch.set_printoptions(precision=10)
def gelu(x):
"""Implementation of the gelu activation function.
For information: OpenAI GPT's gelu is slightly different (and gives slightly different results):
0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3))))
"""
return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0)))
class BertConfig(object):
"""Configuration class to store the configuration of a `BertModel`.
"""
def __init__(self,
vocab_size,
hidden_size=768,
num_hidden_layers=12,
num_attention_heads=12,
intermediate_size=3072,
hidden_act="gelu",
hidden_dropout_prob=0.1,
attention_probs_dropout_prob=0.1,
max_position_embeddings=512,
type_vocab_size=16,
initializer_range=0.02):
"""Constructs BertConfig.
Args:
vocab_size: Vocabulary size of `inputs_ids` in `BertModel`.
hidden_size: Size of the encoder layers and the pooler layer.
num_hidden_layers: Number of hidden layers in the Transformer encoder.
num_attention_heads: Number of attention heads for each attention layer in
the Transformer encoder.
intermediate_size: The size of the "intermediate" (i.e., feed-forward)
layer in the Transformer encoder.
hidden_act: The non-linear activation function (function or string) in the
encoder and pooler.
hidden_dropout_prob: The dropout probabilitiy for all fully connected
layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob: The dropout ratio for the attention
probabilities.
max_position_embeddings: The maximum sequence length that this model might
ever be used with. Typically set this to something large just in case
(e.g., 512 or 1024 or 2048).
type_vocab_size: The vocabulary size of the `token_type_ids` passed into
`BertModel`.
initializer_range: The sttdev of the truncated_normal_initializer for
initializing all weight matrices.
"""
self.vocab_size = vocab_size
self.hidden_size = hidden_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.hidden_act = hidden_act
self.intermediate_size = intermediate_size
self.hidden_dropout_prob = hidden_dropout_prob
self.attention_probs_dropout_prob = attention_probs_dropout_prob
self.max_position_embeddings = max_position_embeddings
self.type_vocab_size = type_vocab_size
self.initializer_range = initializer_range
@classmethod
def from_dict(cls, json_object):
"""Constructs a `BertConfig` from a Python dictionary of parameters."""
config = BertConfig(vocab_size=None)
for (key, value) in six.iteritems(json_object):
config.__dict__[key] = value
return config
@classmethod
def from_json_file(cls, json_file):
"""Constructs a `BertConfig` from a json file of parameters."""
with open(json_file, "r") as reader:
text = reader.read()
return cls.from_dict(json.loads(text))
def to_dict(self):
"""Serializes this instance to a Python dictionary."""
output = copy.deepcopy(self.__dict__)
return output
def to_json_string(self):
"""Serializes this instance to a JSON string."""
return json.dumps(self.to_dict(), indent=2, sort_keys=True) + "\n"
class BERTLayerNorm(nn.Module):
def __init__(self, config, variance_epsilon=1e-12):
"""Construct a layernorm module in the TF style (epsilon inside the square root).
"""
super(BERTLayerNorm, self).__init__()
self.gamma = nn.Parameter(torch.ones(config.hidden_size))
self.beta = nn.Parameter(torch.zeros(config.hidden_size))
self.variance_epsilon = variance_epsilon
def forward(self, x):
u = x.mean(-1, keepdim=True)
s = (x - u).pow(2).mean(-1, keepdim=True)
x = (x - u) / torch.sqrt(s + self.variance_epsilon)
return self.gamma * x + self.beta
class BERTEmbeddings(nn.Module):
def __init__(self, config):
super(BERTEmbeddings, self).__init__()
"""Construct the embedding module from word, position and token_type embeddings.
"""
self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size)
self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size)
self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size)
# self.LayerNorm is not snake-cased to stick with TensorFlow model variable name and be able to load
# any TensorFlow checkpoint file
self.LayerNorm = BERTLayerNorm(config)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
def forward(self, input_ids, token_type_ids=None):
seq_length = input_ids.size(1)
position_ids = torch.arange(seq_length, dtype=torch.long, device=input_ids.device)
position_ids = position_ids.unsqueeze(0).expand_as(input_ids)
if token_type_ids is None:
token_type_ids = torch.zeros_like(input_ids)
words_embeddings = self.word_embeddings(input_ids)
position_embeddings = self.position_embeddings(position_ids)
token_type_embeddings = self.token_type_embeddings(token_type_ids)
embeddings = words_embeddings + position_embeddings + token_type_embeddings
embeddings = self.LayerNorm(embeddings)
embeddings = self.dropout(embeddings)
return embeddings
class BERTSelfAttention(nn.Module):
def __init__(self, config):
super(BERTSelfAttention, self).__init__()
if config.hidden_size % config.num_attention_heads != 0:
raise ValueError(
"The hidden size (%d) is not a multiple of the number of attention "
"heads (%d)" % (config.hidden_size, config.num_attention_heads))
self.num_attention_heads = config.num_attention_heads
self.attention_head_size = int(config.hidden_size / config.num_attention_heads)
self.all_head_size = self.num_attention_heads * self.attention_head_size
self.query = nn.Linear(config.hidden_size, self.all_head_size)
self.key = nn.Linear(config.hidden_size, self.all_head_size)
self.value = nn.Linear(config.hidden_size, self.all_head_size)
self.dropout = nn.Dropout(config.attention_probs_dropout_prob)
def transpose_for_scores(self, x):
new_x_shape = x.size()[:-1] + (self.num_attention_heads, self.attention_head_size)
x = x.view(*new_x_shape)
return x.permute(0, 2, 1, 3)
def forward(self, hidden_states, attention_mask):
mixed_query_layer = self.query(hidden_states)
mixed_key_layer = self.key(hidden_states)
mixed_value_layer = self.value(hidden_states)
query_layer = self.transpose_for_scores(mixed_query_layer)
key_layer = self.transpose_for_scores(mixed_key_layer)
value_layer = self.transpose_for_scores(mixed_value_layer)
# Take the dot product between "query" and "key" to get the raw attention scores.
attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2))
attention_scores = attention_scores / math.sqrt(self.attention_head_size)
# Apply the attention mask is (precomputed for all layers in BertModel forward() function)
attention_scores = attention_scores + attention_mask
# Normalize the attention scores to probabilities.
attention_probs = nn.Softmax(dim=-1)(attention_scores)
# This is actually dropping out entire tokens to attend to, which might
# seem a bit unusual, but is taken from the original Transformer paper.
attention_probs = self.dropout(attention_probs)
context_layer = torch.matmul(attention_probs, value_layer)
context_layer = context_layer.permute(0, 2, 1, 3).contiguous()
new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
context_layer = context_layer.view(*new_context_layer_shape)
return context_layer
class BERTSelfOutput(nn.Module):
def __init__(self, config):
super(BERTSelfOutput, self).__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
self.LayerNorm = BERTLayerNorm(config)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
def forward(self, hidden_states, input_tensor):
hidden_states = self.dense(hidden_states)
hidden_states = self.dropout(hidden_states)
hidden_states = self.LayerNorm(hidden_states + input_tensor)
return hidden_states
class BERTAttention(nn.Module):
def __init__(self, config):
super(BERTAttention, self).__init__()
self.self = BERTSelfAttention(config)
self.output = BERTSelfOutput(config)
def forward(self, input_tensor, attention_mask):
self_output = self.self(input_tensor, attention_mask)
attention_output = self.output(self_output, input_tensor)
return attention_output
class BERTIntermediate(nn.Module):
def __init__(self, config):
super(BERTIntermediate, self).__init__()
self.dense = nn.Linear(config.hidden_size, config.intermediate_size)
self.intermediate_act_fn = gelu
def forward(self, hidden_states):
hidden_states = self.dense(hidden_states)
hidden_states = self.intermediate_act_fn(hidden_states)
return hidden_states
class BERTOutput(nn.Module):
def __init__(self, config):
super(BERTOutput, self).__init__()
self.dense = nn.Linear(config.intermediate_size, config.hidden_size)
self.LayerNorm = BERTLayerNorm(config)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
def forward(self, hidden_states, input_tensor):
hidden_states = self.dense(hidden_states)
hidden_states = self.dropout(hidden_states)
hidden_states = self.LayerNorm(hidden_states + input_tensor)
return hidden_states
class BERTLayer(nn.Module):
def __init__(self, config):
super(BERTLayer, self).__init__()
self.attention = BERTAttention(config)
self.intermediate = BERTIntermediate(config)
self.output = BERTOutput(config)
def forward(self, hidden_states, attention_mask):
attention_output = self.attention(hidden_states, attention_mask)
intermediate_output = self.intermediate(attention_output)
layer_output = self.output(intermediate_output, attention_output)
return layer_output
class FreezeBERTEncoder(nn.Module):
def __init__(self, config):
super(FreezeBERTEncoder, self).__init__()
layer = BERTLayer(config)
self.layer = nn.ModuleList([copy.deepcopy(layer) for _ in range(config.num_hidden_layers)])
def forward(self, hidden_states, attention_mask, start_layer=None, prev_min_trainable_layer=None, bert_last=None, caching=False, caching_training=False):
all_encoder_layers = []
layer_num = 0
if start_layer > 0 and caching_training is True:
if bert_last is not None:
hidden_states = bert_last
for i in range(prev_min_trainable_layer, len(self.layer)):
if i < start_layer:
self.layer[i].eval()
with torch.no_grad():
hidden_states = self.layer[i](hidden_states, attention_mask)
all_encoder_layers.append(hidden_states)
else:
hidden_states = self.layer[i](hidden_states, attention_mask)
all_encoder_layers.append(hidden_states)
else:
for i in range(0, len(self.layer)):
if i < start_layer:
self.layer[i].eval()
with torch.no_grad():
hidden_states = self.layer[i](hidden_states, attention_mask)
else:
hidden_states = self.layer[i](hidden_states, attention_mask)
all_encoder_layers.append(hidden_states)
else:
if start_layer == 0:
for layer_module in self.layer:
hidden_states = layer_module(hidden_states, attention_mask)
all_encoder_layers.append(hidden_states)
layer_num += 1
else:
for i in range(0, len(self.layer)):
if i < start_layer:
self.layer[i].eval()
with torch.no_grad():
hidden_states = self.layer[i](hidden_states, attention_mask)
else:
hidden_states = self.layer[i](hidden_states, attention_mask)
all_encoder_layers.append(hidden_states)
return all_encoder_layers
class TestBERTEncoder(nn.Module):
def __init__(self, config):
super(TestBERTEncoder, self).__init__()
layer = BERTLayer(config)
self.layer = nn.ModuleList([copy.deepcopy(layer) for _ in range(config.num_hidden_layers)])
def forward(self, hidden_states, attention_mask, start_layer=None, prev_min_trainable_layer=None, bert_last=None, caching=False, caching_training=False):
all_encoder_layers = []
layer_num = 0
for i in range(0, start_layer):
self.layer[i].eval()
with torch.no_grad():
hidden_states = self.layer[i](hidden_states, attention_mask)
all_encoder_layers.append(hidden_states)
return all_encoder_layers
class BERTPooler(nn.Module):
def __init__(self, config):
super(BERTPooler, self).__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
self.activation = nn.Tanh()
def forward(self, hidden_states):
# We "pool" the model by simply taking the hidden state corresponding
# to the first token.
first_token_tensor = hidden_states[:, 0]
pooled_output = self.dense(first_token_tensor)
pooled_output = self.activation(pooled_output)
return pooled_output
class TestBertModel(nn.Module):
"""BERT model ("Bidirectional Embedding Representations from a Transformer").
Example usage:
```python
# Already been converted into WordPiece token ids
input_ids = torch.LongTensor([[31, 51, 99], [15, 5, 0]])
input_mask = torch.LongTensor([[1, 1, 1], [1, 1, 0]])
token_type_ids = torch.LongTensor([[0, 0, 1], [0, 2, 0]])
config = modeling.BertConfig(vocab_size=32000, hidden_size=512,
num_hidden_layers=8, num_attention_heads=6, intermediate_size=1024)
model = modeling.BertModel(config=config)
all_encoder_layers, pooled_output = model(input_ids, token_type_ids, input_mask)
```
"""
def __init__(self, config: BertConfig):
"""Constructor for BertModel.
Args:
config: `BertConfig` instance.
"""
super(TestBertModel, self).__init__()
self.embeddings = BERTEmbeddings(config)
self.encoder = TestBERTEncoder(config)
self.pooler = BERTPooler(config)
def forward(self, input_ids, token_type_ids=None, attention_mask=None, start_layer=None, prev_min_trainable_layer=None, bert_last=None, caching=False, caching_training=False):
if attention_mask is None:
attention_mask = torch.ones_like(input_ids)
if token_type_ids is None:
token_type_ids = torch.zeros_like(input_ids)
# We create a 3D attention mask from a 2D tensor mask.
# Sizes are [batch_size, 1, 1, from_seq_length]
# So we can broadcast to [batch_size, num_heads, to_seq_length, from_seq_length]
# this attention mask is more simple than the triangular masking of causal attention
# used in OpenAI GPT, we just need to prepare the broadcast dimension here.
extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)
# Since attention_mask is 1.0 for positions we want to attend and 0.0 for
# masked positions, this operation will create a tensor which is 0.0 for
# positions we want to attend and -10000.0 for masked positions.
# Since we are adding it to the raw scores before the softmax, this is
# effectively the same as removing these entirely.
extended_attention_mask = extended_attention_mask.float()
extended_attention_mask = (1.0 - extended_attention_mask) * -10000.0
self.embeddings.eval()
with torch.no_grad():
embedding_output = self.embeddings(input_ids, token_type_ids)
all_encoder_layers = self.encoder(embedding_output, extended_attention_mask, start_layer=start_layer, prev_min_trainable_layer=prev_min_trainable_layer, bert_last=bert_last, caching=caching, caching_training=caching_training)
sequence_output = all_encoder_layers[-1]
pooled_output = self.pooler(sequence_output)
return all_encoder_layers, pooled_output
class FreezeBertModel(nn.Module):
"""BERT model ("Bidirectional Embedding Representations from a Transformer").
Example usage:
```python
# Already been converted into WordPiece token ids
input_ids = torch.LongTensor([[31, 51, 99], [15, 5, 0]])
input_mask = torch.LongTensor([[1, 1, 1], [1, 1, 0]])
token_type_ids = torch.LongTensor([[0, 0, 1], [0, 2, 0]])
config = modeling.BertConfig(vocab_size=32000, hidden_size=512,
num_hidden_layers=8, num_attention_heads=6, intermediate_size=1024)
model = modeling.BertModel(config=config)
all_encoder_layers, pooled_output = model(input_ids, token_type_ids, input_mask)
```
"""
def __init__(self, config: BertConfig):
"""Constructor for BertModel.
Args:
config: `BertConfig` instance.
"""
super(FreezeBertModel, self).__init__()
self.embeddings = BERTEmbeddings(config)
self.encoder = FreezeBERTEncoder(config)
self.pooler = BERTPooler(config)
def forward(self, input_ids, token_type_ids=None, attention_mask=None, start_layer=None, prev_min_trainable_layer=None, bert_last=None, caching=False, caching_training=False):
if attention_mask is None:
attention_mask = torch.ones_like(input_ids)
if token_type_ids is None:
token_type_ids = torch.zeros_like(input_ids)
# We create a 3D attention mask from a 2D tensor mask.
# Sizes are [batch_size, 1, 1, from_seq_length]
# So we can broadcast to [batch_size, num_heads, to_seq_length, from_seq_length]
# this attention mask is more simple than the triangular masking of causal attention
# used in OpenAI GPT, we just need to prepare the broadcast dimension here.
extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)
# Since attention_mask is 1.0 for positions we want to attend and 0.0 for
# masked positions, this operation will create a tensor which is 0.0 for
# positions we want to attend and -10000.0 for masked positions.
# Since we are adding it to the raw scores before the softmax, this is
# effectively the same as removing these entirely.
extended_attention_mask = extended_attention_mask.float()
extended_attention_mask = (1.0 - extended_attention_mask) * -10000.0
if start_layer is not None and start_layer > 0:
self.embeddings.eval()
with torch.no_grad():
embedding_output = self.embeddings(input_ids, token_type_ids)
else:
embedding_output = self.embeddings(input_ids, token_type_ids)
all_encoder_layers = self.encoder(embedding_output, extended_attention_mask, start_layer=start_layer, prev_min_trainable_layer=prev_min_trainable_layer, bert_last=bert_last, caching=caching, caching_training=caching_training)
sequence_output = all_encoder_layers[-1]
# print(sequence_output)
pooled_output = self.pooler(sequence_output)
return all_encoder_layers, pooled_output
class BertForSequenceClassification(nn.Module):
def __init__(self, config, num_labels, layers=None, pooling=None):
super(BertForSequenceClassification, self).__init__()
self.bert = FreezeBertModel(config)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.pooling = pooling
if layers is None or layers[0] == -2:
self.layers = []
elif layers[0] == -1:
self.layers = [i for i in range(config.num_hidden_layers)]
else:
self.layers = layers
self.num_labels = num_labels
self.classifier = nn.Linear(
config.hidden_size, num_labels)
def init_weights(module):
if isinstance(module, (nn.Linear, nn.Embedding)):
# Slightly different from the TF version which uses truncated_normal for initialization
# cf https://github.com/pytorch/pytorch/pull/5617
module.weight.data.normal_(mean=0.0, std=config.initializer_range)
elif isinstance(module, BERTLayerNorm):
module.beta.data.normal_(mean=0.0, std=config.initializer_range)
module.gamma.data.normal_(mean=0.0, std=config.initializer_range)
if isinstance(module, nn.Linear):
module.bias.data.zero_()
self.apply(init_weights)
print("!!!!!!!!!!!!!!!!!")
def forward(self, input_ids, token_type_ids, attention_mask, labels=None, start_layer=0, prev_min_trainable_layer=0, bert_last=None, caching=False, caching_training=False):
r"""
labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
Labels for computing the sequence classification/regression loss.
Indices should be in :obj:`[0, ..., config.num_labels - 1]`.
If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
If :obj:`config.num_labels > 1` a classification loss is computed (Cross-Entropy).
Returns:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`label` is provided):
Classification (or regression if config.num_labels==1) loss.
logits (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, config.num_labels)`):
Classification (or regression if config.num_labels==1) scores (before SoftMax).
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(batch_size, num_heads, sequence_length, sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
Examples::
from transformers import BertTokenizer, BertForSequenceClassification
import torch
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0) # Batch size 1
labels = torch.tensor([1]).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=labels)
loss, logits = outputs[:2]
"""
encoded_layers, pooled_output = self.bert(input_ids, token_type_ids, attention_mask, start_layer, prev_min_trainable_layer, bert_last, caching, caching_training)
# print(pooled_output[0])
pooled_output = self.dropout(pooled_output)
logits = self.classifier(pooled_output)
outputs = (logits,) # add hidden states and attention if they are here
if labels is not None:
if self.num_labels == 1:
# We are doing regression
loss_fct = MSELoss()
loss = loss_fct(logits.view(-1), labels.view(-1))
else:
loss_fct = CrossEntropyLoss()
loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
outputs = (loss,) + outputs
return outputs, encoded_layers # (loss), logits, (hidden_states), (attentions)
class BertForSequenceClassificationTest(nn.Module):
def __init__(self, config, num_labels, layers=None, pooling=None):
super(BertForSequenceClassificationTest, self).__init__()
self.bert = TestBertModel(config)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.pooling = pooling
if layers is None or layers[0] == -2:
self.layers = []
elif layers[0] == -1:
self.layers = [i for i in range(config.num_hidden_layers)]
else:
self.layers = layers
self.num_labels = num_labels
self.classifier = nn.Linear(
config.hidden_size, num_labels)
def init_weights(module):
if isinstance(module, (nn.Linear, nn.Embedding)):
# Slightly different from the TF version which uses truncated_normal for initialization
# cf https://github.com/pytorch/pytorch/pull/5617
module.weight.data.normal_(mean=0.0, std=config.initializer_range)
elif isinstance(module, BERTLayerNorm):
module.beta.data.normal_(mean=0.0, std=config.initializer_range)
module.gamma.data.normal_(mean=0.0, std=config.initializer_range)
if isinstance(module, nn.Linear):
module.bias.data.zero_()
self.apply(init_weights)
print("!!!!!!!!!!!!!!!!!")
def forward(self, input_ids, token_type_ids, attention_mask, labels=None, start_layer=0, prev_min_trainable_layer=0, bert_last=None, caching=False, caching_training=False):
r"""
labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
Labels for computing the sequence classification/regression loss.
Indices should be in :obj:`[0, ..., config.num_labels - 1]`.
If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
If :obj:`config.num_labels > 1` a classification loss is computed (Cross-Entropy).
Returns:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`label` is provided):
Classification (or regression if config.num_labels==1) loss.
logits (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, config.num_labels)`):
Classification (or regression if config.num_labels==1) scores (before SoftMax).
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(batch_size, num_heads, sequence_length, sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
Examples::
from transformers import BertTokenizer, BertForSequenceClassification
import torch
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0) # Batch size 1
labels = torch.tensor([1]).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=labels)
loss, logits = outputs[:2]
"""
encoded_layers, pooled_output = self.bert(input_ids, token_type_ids, attention_mask, start_layer, prev_min_trainable_layer, bert_last, caching, caching_training)
# print(pooled_output[0])
pooled_output = self.dropout(pooled_output)
logits = self.classifier(pooled_output)
outputs = (logits,) # add hidden states and attention if they are here
if labels is not None:
if self.num_labels == 1:
# We are doing regression
loss_fct = MSELoss()
loss = loss_fct(logits.view(-1), labels.view(-1))
else:
loss_fct = CrossEntropyLoss()
loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
outputs = (loss,) + outputs
return outputs, encoded_layers # (loss), logits, (hidden_states), (attentions)