-
Notifications
You must be signed in to change notification settings - Fork 18
/
modeling.py
1330 lines (1147 loc) · 64.8 KB
/
modeling.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
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# coding=utf-8
# Copyright (c) 2019, Facebook, Inc. and its affiliates. All Rights Reserved
# 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, division, print_function, unicode_literals
import copy
import json
import logging
import math
import os
import shutil
import tarfile
import tempfile
import sys
import time
from io import open
import torch
from torch import nn
from torch.nn import CrossEntropyLoss,MarginRankingLoss, NLLLoss
from torch.nn import Softmax
import torch.nn.functional as F
from .file_utils import cached_path, WEIGHTS_NAME, CONFIG_NAME
logger = logging.getLogger(__name__)
PRETRAINED_MODEL_ARCHIVE_MAP = {
'bert-base-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased.tar.gz",
'bert-large-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased.tar.gz",
'bert-base-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased.tar.gz",
'bert-large-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased.tar.gz",
'spanbert-base-cased': "https://dl.fbaipublicfiles.com/fairseq/models/spanbert_hf_base.tar.gz",
'spanbert-large-cased': "https://dl.fbaipublicfiles.com/fairseq/models/spanbert_hf.tar.gz"
}
BERT_CONFIG_NAME = 'bert_config.json'
TF_WEIGHTS_NAME = 'model.ckpt'
def load_tf_weights_in_bert(model, tf_checkpoint_path):
""" Load tf checkpoints in a pytorch model
"""
try:
import re
import numpy as np
import tensorflow as tf
except ImportError:
print("Loading a TensorFlow models in PyTorch, requires TensorFlow to be installed. Please see "
"https://www.tensorflow.org/install/ for installation instructions.")
raise
tf_path = os.path.abspath(tf_checkpoint_path)
print("Converting TensorFlow checkpoint from {}".format(tf_path))
# Load weights from TF model
init_vars = tf.train.list_variables(tf_path)
names = []
arrays = []
for name, shape in init_vars:
print("Loading TF weight {} with shape {}".format(name, shape))
array = tf.train.load_variable(tf_path, name)
names.append(name)
arrays.append(array)
for name, array in zip(names, arrays):
name = name.split('/')
# adam_v and adam_m are variables used in AdamWeightDecayOptimizer to calculated m and v
# which are not required for using pretrained model
if any(n in ["adam_v", "adam_m", "global_step"] for n in name):
print("Skipping {}".format("/".join(name)))
continue
pointer = model
for m_name in name:
if re.fullmatch(r'[A-Za-z]+_\d+', m_name):
l = re.split(r'_(\d+)', m_name)
else:
l = [m_name]
if l[0] == 'kernel' or l[0] == 'gamma':
pointer = getattr(pointer, 'weight')
elif l[0] == 'output_bias' or l[0] == 'beta':
pointer = getattr(pointer, 'bias')
elif l[0] == 'output_weights':
pointer = getattr(pointer, 'weight')
elif l[0] == 'squad':
pointer = getattr(pointer, 'classifier')
else:
try:
pointer = getattr(pointer, l[0])
except AttributeError:
print("Skipping {}".format("/".join(name)))
continue
if len(l) >= 2:
num = int(l[1])
pointer = pointer[num]
if m_name[-11:] == '_embeddings':
pointer = getattr(pointer, 'weight')
elif m_name == 'kernel':
array = np.transpose(array)
try:
assert pointer.shape == array.shape
except AssertionError as e:
e.args += (pointer.shape, array.shape)
raise
print("Initialize PyTorch weight {}".format(name))
pointer.data = torch.from_numpy(array)
return model
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))))
Also see https://arxiv.org/abs/1606.08415
"""
return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0)))
def swish(x):
return x * torch.sigmoid(x)
ACT2FN = {"gelu": gelu, "relu": torch.nn.functional.relu, "swish": swish}
class BertConfig(object):
"""Configuration class to store the configuration of a `BertModel`.
"""
def __init__(self,
vocab_size_or_config_json_file,
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=2,
initializer_range=0.02):
"""Constructs BertConfig.
Args:
vocab_size_or_config_json_file: 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. If string, "gelu", "relu" and "swish" are supported.
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.
"""
if isinstance(vocab_size_or_config_json_file, str) or (sys.version_info[0] == 2
and isinstance(vocab_size_or_config_json_file, unicode)):
with open(vocab_size_or_config_json_file, "r", encoding='utf-8') as reader:
json_config = json.loads(reader.read())
for key, value in json_config.items():
self.__dict__[key] = value
elif isinstance(vocab_size_or_config_json_file, int):
self.vocab_size = vocab_size_or_config_json_file
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
else:
raise ValueError("First argument must be either a vocabulary size (int)"
"or the path to a pretrained model config file (str)")
@classmethod
def from_dict(cls, json_object):
"""Constructs a `BertConfig` from a Python dictionary of parameters."""
config = BertConfig(vocab_size_or_config_json_file=-1)
for key, value in json_object.items():
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", encoding='utf-8') as reader:
text = reader.read()
return cls.from_dict(json.loads(text))
def __repr__(self):
return str(self.to_json_string())
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"
def to_json_file(self, json_file_path):
""" Save this instance to a json file."""
with open(json_file_path, "w", encoding='utf-8') as writer:
writer.write(self.to_json_string())
# try:
# from apex.normalization.fused_layer_norm import FusedLayerNorm as BertLayerNorm
# except ImportError:
# logger.info("Better speed can be achieved with apex installed from https://www.github.com/nvidia/apex .")
class BertLayerNorm(nn.Module):
def __init__(self, hidden_size, eps=1e-12):
"""Construct a layernorm module in the TF style (epsilon inside the square root).
"""
super(BertLayerNorm, self).__init__()
self.weight = nn.Parameter(torch.ones(hidden_size))
self.bias = nn.Parameter(torch.zeros(hidden_size))
self.variance_epsilon = eps
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.weight * x + self.bias
class BertEmbeddings(nn.Module):
"""Construct the embeddings from word, position and token_type embeddings.
"""
def __init__(self, config):
super(BertEmbeddings, self).__init__()
self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=0)
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.hidden_size, eps=1e-12)
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, output_attentions=False):
# attention_mask: batch_size*1*1*seq_length
mixed_query_layer = self.query(hidden_states)
mixed_key_layer = self.key(hidden_states)
mixed_value_layer = self.value(hidden_states)
# batch_size*num_attention_heads*seq_length*attention_head_size
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.
# batch_size*num_attention_heads*seq_length*seq_length
attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2))
# assert not torch.isnan(attention_scores).any()
attention_scores = attention_scores / math.sqrt(self.attention_head_size)
# assert not torch.isnan(attention_scores).any()
attention_scores = torch.clamp(attention_scores, -10000., 10000.)
# 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)
outputs = (context_layer, attention_probs) if output_attentions else (context_layer,)
return outputs
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.hidden_size, eps=1e-12)
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, output_attentions=False):
self_outputs = self.self(input_tensor, attention_mask, output_attentions)
attention_output = self_outputs[0]
attention_output = self.output(attention_output, input_tensor)
outputs = (attention_output,) + self_outputs[1:] # add attentions if we output them
return outputs
class BertIntermediate(nn.Module):
def __init__(self, config):
super(BertIntermediate, self).__init__()
self.dense = nn.Linear(config.hidden_size, config.intermediate_size)
if isinstance(config.hidden_act, str) or (sys.version_info[0] == 2 and isinstance(config.hidden_act, unicode)):
self.intermediate_act_fn = ACT2FN[config.hidden_act]
else:
self.intermediate_act_fn = config.hidden_act
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.hidden_size, eps=1e-12)
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, output_attentions=False):
self_attention_outputs = self.attention(hidden_states, attention_mask, output_attentions=output_attentions)
attention_output = self_attention_outputs[0]
intermediate_output = self.intermediate(attention_output)
layer_output = self.output(intermediate_output, attention_output)
attentions = self_attention_outputs[1:] # add self attentions if we output attention weights
outputs = (layer_output,) + attentions
return outputs
class BertEncoder(nn.Module):
def __init__(self, config):
super(BertEncoder, 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, output_all_encoded_layers=True, output_attentions=False):
all_encoder_layers = []
for layer_module in self.layer:
layer_outputs = layer_module(hidden_states, attention_mask, output_attentions) # Tuple(layer output, attention)
if output_all_encoded_layers:
all_encoder_layers.append(layer_outputs)
hidden_states = layer_outputs[0]
if not output_all_encoded_layers:
all_encoder_layers.append(layer_outputs)
return all_encoder_layers # (layer_output,) + attentions
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 BertPredictionHeadTransform(nn.Module):
def __init__(self, config):
super(BertPredictionHeadTransform, self).__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
if isinstance(config.hidden_act, str) or (sys.version_info[0] == 2 and isinstance(config.hidden_act, unicode)):
self.transform_act_fn = ACT2FN[config.hidden_act]
else:
self.transform_act_fn = config.hidden_act
self.LayerNorm = BertLayerNorm(config.hidden_size, eps=1e-12)
def forward(self, hidden_states):
hidden_states = self.dense(hidden_states)
hidden_states = self.transform_act_fn(hidden_states)
hidden_states = self.LayerNorm(hidden_states)
return hidden_states
class BertLMPredictionHead(nn.Module):
def __init__(self, config, bert_model_embedding_weights):
super(BertLMPredictionHead, self).__init__()
self.transform = BertPredictionHeadTransform(config)
# The output weights are the same as the input embeddings, but there is
# an output-only bias for each token.
self.decoder = nn.Linear(bert_model_embedding_weights.size(1),
bert_model_embedding_weights.size(0),
bias=False)
self.decoder.weight = bert_model_embedding_weights
self.bias = nn.Parameter(torch.zeros(bert_model_embedding_weights.size(0)))
def forward(self, hidden_states):
hidden_states = self.transform(hidden_states)
hidden_states = self.decoder(hidden_states) + self.bias
return hidden_states
class BertOnlyMLMHead(nn.Module):
def __init__(self, config, bert_model_embedding_weights):
super(BertOnlyMLMHead, self).__init__()
self.predictions = BertLMPredictionHead(config, bert_model_embedding_weights)
def forward(self, sequence_output):
prediction_scores = self.predictions(sequence_output)
return prediction_scores
class BertOnlyNSPHead(nn.Module):
def __init__(self, config):
super(BertOnlyNSPHead, self).__init__()
self.seq_relationship = nn.Linear(config.hidden_size, 2)
def forward(self, pooled_output):
seq_relationship_score = self.seq_relationship(pooled_output)
return seq_relationship_score
class BertPreTrainingHeads(nn.Module):
def __init__(self, config, bert_model_embedding_weights):
super(BertPreTrainingHeads, self).__init__()
self.predictions = BertLMPredictionHead(config, bert_model_embedding_weights)
self.seq_relationship = nn.Linear(config.hidden_size, 2)
def forward(self, sequence_output, pooled_output):
prediction_scores = self.predictions(sequence_output)
seq_relationship_score = self.seq_relationship(pooled_output)
return prediction_scores, seq_relationship_score
class BertPreTrainedModel(nn.Module):
""" An abstract class to handle weights initialization and
a simple interface for dowloading and loading pretrained models.
"""
def __init__(self, config, *inputs, **kwargs):
super(BertPreTrainedModel, self).__init__()
if not isinstance(config, BertConfig):
raise ValueError(
"Parameter config in `{}(config)` should be an instance of class `BertConfig`. "
"To create a model from a Google pretrained model use "
"`model = {}.from_pretrained(PRETRAINED_MODEL_NAME)`".format(
self.__class__.__name__, self.__class__.__name__
))
self.config = config
def init_bert_weights(self, module):
""" Initialize the weights.
"""
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=self.config.initializer_range)
elif isinstance(module, BertLayerNorm):
module.bias.data.zero_()
module.weight.data.fill_(1.0)
if isinstance(module, nn.Linear) and module.bias is not None:
module.bias.data.zero_()
@classmethod
def from_pretrained(cls, pretrained_model_name_or_path, state_dict=None, cache_dir=None,
from_tf=False, *inputs, **kwargs):
"""
Instantiate a BertPreTrainedModel from a pre-trained model file or a pytorch state dict.
Download and cache the pre-trained model file if needed.
Params:
pretrained_model_name_or_path: either:
- a str with the name of a pre-trained model to load selected in the list of:
. `bert-base-uncased`
. `bert-large-uncased`
. `bert-base-cased`
. `bert-large-cased`
. `bert-base-multilingual-uncased`
. `bert-base-multilingual-cased`
. `bert-base-chinese`
- a path or url to a pretrained model archive containing:
. `bert_config.json` a configuration file for the model
. `pytorch_model.bin` a PyTorch dump of a BertForPreTraining instance
- a path or url to a pretrained model archive containing:
. `bert_config.json` a configuration file for the model
. `model.chkpt` a TensorFlow checkpoint
from_tf: should we load the weights from a locally saved TensorFlow checkpoint
cache_dir: an optional path to a folder in which the pre-trained models will be cached.
state_dict: an optional state dictionnary (collections.OrderedDict object) to use instead of Google pre-trained models
*inputs, **kwargs: additional input for the specific Bert class
(ex: num_labels for BertForSequenceClassification)
"""
if pretrained_model_name_or_path in PRETRAINED_MODEL_ARCHIVE_MAP:
archive_file = PRETRAINED_MODEL_ARCHIVE_MAP[pretrained_model_name_or_path]
else:
archive_file = pretrained_model_name_or_path
# redirect to the cache, if necessary
try:
resolved_archive_file = cached_path(archive_file, cache_dir=cache_dir)
except EnvironmentError:
logger.error(
"Model name '{}' was not found in model name list ({}). "
"We assumed '{}' was a path or url but couldn't find any file "
"associated to this path or url.".format(
pretrained_model_name_or_path,
', '.join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()),
archive_file))
return None
if resolved_archive_file == archive_file:
logger.info("loading archive file {}".format(archive_file))
else:
logger.info("loading archive file {} from cache at {}".format(
archive_file, resolved_archive_file))
tempdir = None
if os.path.isdir(resolved_archive_file) or from_tf:
serialization_dir = resolved_archive_file
else:
# Extract archive to temp dir
tempdir = tempfile.mkdtemp()
logger.info("extracting archive file {} to temp dir {}".format(
resolved_archive_file, tempdir))
with tarfile.open(resolved_archive_file, 'r:gz') as archive:
archive.extractall(tempdir)
serialization_dir = tempdir
# Load config
config_file = os.path.join(serialization_dir, CONFIG_NAME)
if not os.path.exists(config_file):
# Backward compatibility with old naming format
config_file = os.path.join(serialization_dir, BERT_CONFIG_NAME)
config = BertConfig.from_json_file(config_file)
if pretrained_model_name_or_path == 'bert-base-uncased-1024':
config.max_position_embeddings = 1024
logger.info("Model config {}".format(config))
# Instantiate model.
model = cls(config, *inputs, **kwargs)
if state_dict is None and not from_tf:
weights_path = os.path.join(serialization_dir, WEIGHTS_NAME)
state_dict = torch.load(weights_path, map_location='cpu')
if tempdir:
# Clean up temp dir
shutil.rmtree(tempdir)
if from_tf:
# Directly load from a TensorFlow checkpoint
weights_path = os.path.join(serialization_dir, TF_WEIGHTS_NAME)
return load_tf_weights_in_bert(model, weights_path)
# Load from a PyTorch state_dict
old_keys = []
new_keys = []
for key in state_dict.keys():
new_key = key[8:] if key.startswith("decoder.") else key
if 'gamma' in new_key:
new_key = new_key.replace('gamma', 'weight')
if 'beta' in new_key:
new_key = new_key.replace('beta', 'bias')
if key != new_key:
old_keys.append(key)
new_keys.append(new_key)
for old_key, new_key in zip(old_keys, new_keys):
state_dict[new_key] = state_dict.pop(old_key)
missing_keys = []
unexpected_keys = []
error_msgs = []
# copy state_dict so _load_from_state_dict can modify it
metadata = getattr(state_dict, '_metadata', None)
state_dict = state_dict.copy()
if metadata is not None:
state_dict._metadata = metadata
def load(module, prefix=''):
local_metadata = {} if metadata is None else metadata.get(prefix[:-1], {})
module._load_from_state_dict(
state_dict, prefix, local_metadata, True, missing_keys, unexpected_keys, error_msgs)
for name, child in module._modules.items():
if child is not None:
load(child, prefix + name + '.')
start_prefix = ''
if not hasattr(model, 'bert') and any(s.startswith('bert.') for s in state_dict.keys()):
start_prefix = 'bert.'
load(model, prefix=start_prefix)
if len(missing_keys) > 0:
logger.info("Weights of {} not initialized from pretrained model: {}".format(
model.__class__.__name__, missing_keys))
if len(unexpected_keys) > 0:
logger.info("Weights from pretrained model not used in {}: {}".format(
model.__class__.__name__, unexpected_keys))
if len(error_msgs) > 0:
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
model.__class__.__name__, "\n\t".join(error_msgs)))
return model
class BertModel(BertPreTrainedModel):
"""BERT model ("Bidirectional Embedding Representations from a Transformer").
Params:
config: a BertConfig class instance with the configuration to build a new model
Inputs:
`input_ids`: a torch.LongTensor of shape [batch_size, sequence_length]
with the word token indices in the vocabulary(see the tokens preprocessing logic in the scripts
`extract_features.py`, `run_classifier.py` and `run_squad.py`)
`token_type_ids`: an optional torch.LongTensor of shape [batch_size, sequence_length] with the token
types indices selected in [0, 1]. Type 0 corresponds to a `sentence A` and type 1 corresponds to
a `sentence B` token (see BERT paper for more details).
`attention_mask`: an optional torch.LongTensor of shape [batch_size, sequence_length] with indices
selected in [0, 1]. It's a mask to be used if the input sequence length is smaller than the max
input sequence length in the current batch. It's the mask that we typically use for attention when
a batch has varying length sentences.
`output_all_encoded_layers`: boolean which controls the content of the `encoded_layers` output as described below. Default: `True`.
`output_attentions (:obj:`bool`, `optional`)`:
Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned
tensors for more detail.
Outputs: Tuple of (encoded_layers, pooled_output)
`encoded_layers`: controled by `output_all_encoded_layers` argument:
- `output_all_encoded_layers=True`: outputs a list of the full sequences of encoded-hidden-states at the end
of each attention block (i.e. 12 full sequences for BERT-base, 24 for BERT-large), each
encoded-hidden-state is a torch.FloatTensor of size [batch_size, sequence_length, hidden_size],
- `output_all_encoded_layers=False`: outputs only the full sequence of hidden-states corresponding
to the last attention block of shape [batch_size, sequence_length, hidden_size],
`pooled_output`: a torch.FloatTensor of size [batch_size, hidden_size] which is the output of a
classifier pretrained on top of the hidden state associated to the first character of the
input (`CLS`) to train on the Next-Sentence task (see BERT's paper).
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, 1, 0]])
config = modeling.BertConfig(vocab_size_or_config_json_file=32000, hidden_size=768,
num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072)
model = modeling.BertModel(config=config)
all_encoder_layers, pooled_output = model(input_ids, token_type_ids, input_mask)
```
"""
def __init__(self, config):
super(BertModel, self).__init__(config)
self.embeddings = BertEmbeddings(config)
self.encoder = BertEncoder(config)
self.pooler = BertPooler(config)
self.apply(self.init_bert_weights)
def forward(self, input_ids, token_type_ids=None, attention_mask=None,
output_all_encoded_layers=True, output_attentions=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, to_seq_length]
# So we can broadcast to [batch_size, num_heads, from_seq_length, to_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.
if attention_mask.dim() == 2:
extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)
elif attention_mask.dim() == 3:
extended_attention_mask = attention_mask.unsqueeze(1)
else:
raise NotImplementedError
# extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)
# extended_attention_mask = attention_mask.unsqueeze(1)
# 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.to(dtype=next(self.parameters()).dtype) # fp16 compatibility
extended_attention_mask = (1.0 - extended_attention_mask) * -10000.0
embedding_output = self.embeddings(input_ids, token_type_ids)
encoder_outputs = self.encoder(embedding_output,
extended_attention_mask,
output_all_encoded_layers=output_all_encoded_layers,
output_attentions=output_attentions)
encoded_layers = tuple(layer_output[0] for layer_output in encoder_outputs)
sequence_output = encoded_layers[-1]
pooled_output = self.pooler(sequence_output)
if not output_all_encoded_layers:
encoded_layers = encoded_layers[-1] # (sequence_hidden_states, attention_weight)
if output_attentions:
attention_outputs = tuple(layer_output[1] for layer_output in encoder_outputs)
return encoded_layers, pooled_output, attention_outputs
else:
return encoded_layers, pooled_output
class PROP(BertPreTrainedModel):
"""BERT model with pre-training heads.
This module comprises the BERT model followed by the two pre-training heads:
- the masked language modeling head, and
- the representative word sets predition head.
Params:
config: a BertConfig class instance with the configuration to build a new model.
Inputs:
`input_ids`: a torch.LongTensor of shape [batch_size, sequence_length]
with the word token indices in the vocabulary
`token_type_ids`: an optional torch.LongTensor of shape [batch_size, sequence_length] with the token
types indices selected in [0, 1]. Type 0 corresponds to a `sentence A` and type 1 corresponds to
a `sentence B` token (see BERT paper for more details).
`attention_mask`: an optional torch.LongTensor of shape [batch_size, sequence_length] with indices
selected in [0, 1]. It's a mask to be used if the input sequence length is smaller than the max
input sequence length in the current batch. It's the mask that we typically use for attention when
a batch has varying length sentences.
`masked_lm_labels`: optional masked language modeling labels: torch.LongTensor of shape [batch_size, sequence_length]
with indices selected in [-1, 0, ..., vocab_size]. All labels set to -1 are ignored (masked), the loss
is only computed for the labels set in [0, ..., vocab_size]
`representative_word_sets_label`: optional representative word sets predition(ROP) loss: torch.LongTensor of shape [batch_size]
with indices selected in [0, 1]. We actually do not use it.
Outputs:
if `masked_lm_labels` and `representative_word_sets_label` are not `None`:
Outputs the loss which is the sum of the masked language modeling loss and the representative word sets
predition loss.
if `masked_lm_labels` or `representative_word_sets_label` is `None`:
Outputs a tuple comprising
- the masked language modeling logits of shape [batch_size, sequence_length, vocab_size], and
- the representative word sets logits of shape [batch_size/2, 2].
"""
def __init__(self, config):
super(PROP, self).__init__(config)
self.bert = BertModel(config)
self.cls = BertOnlyMLMHead(config, self.bert.embeddings.word_embeddings.weight)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.cls = nn.Linear(config.hidden_size, 1)
self.cls.predictions = BertLMPredictionHead(config, self.bert.embeddings.word_embeddings.weight)
self.apply(self.init_bert_weights)
def forward(self, input_ids, token_type_ids=None, input_mask=None, masked_lm_labels=None,
representative_word_sets_label=None):
batch_size = input_ids.size(0)
sequence_output, pooled_output = self.bert(input_ids, token_type_ids, input_mask,
output_all_encoded_layers=False)
prediction_scores = self.rep(self.dropout(pooled_output))
if masked_lm_labels is not None and representative_word_sets_label is not None:
# MLM loss
lm_prediction_scores = self.cls.predictions(sequence_output)
loss_fct = CrossEntropyLoss(ignore_index=-1)
masked_lm_loss = loss_fct(lm_prediction_scores.view(-1, self.config.vocab_size), masked_lm_labels.view(-1))
# ROP loss
softmax = Softmax(dim=1)
marginloss = MarginRankingLoss(margin=1.0, reduction='mean')
logits = prediction_scores.reshape(batch_size//2, 2)
logits = softmax(logits)
pos_logits = logits[:, 0]
neg_logits = logits[:, 1]
# `target = 1` assumed the first input should be ranked
# higher (have a larger value) than the second input, and vice-versa
rop_label = torch.ones_like(pos_logits)
rop_loss = marginloss(pos_logits, neg_logits, rop_label)
loss = masked_lm_loss + rop_loss
return loss
else:
return prediction_scores
class BertForPreTraining(BertPreTrainedModel):
"""BERT model with pre-training heads.
This module comprises the BERT model followed by the two pre-training heads:
- the masked language modeling head, and
- the next sentence classification head.
Params:
config: a BertConfig class instance with the configuration to build a new model.
Inputs:
`input_ids`: a torch.LongTensor of shape [batch_size, sequence_length]
with the word token indices in the vocabulary(see the tokens preprocessing logic in the scripts
`extract_features.py`, `run_classifier.py` and `run_squad.py`)
`token_type_ids`: an optional torch.LongTensor of shape [batch_size, sequence_length] with the token
types indices selected in [0, 1]. Type 0 corresponds to a `sentence A` and type 1 corresponds to
a `sentence B` token (see BERT paper for more details).
`attention_mask`: an optional torch.LongTensor of shape [batch_size, sequence_length] with indices
selected in [0, 1]. It's a mask to be used if the input sequence length is smaller than the max
input sequence length in the current batch. It's the mask that we typically use for attention when
a batch has varying length sentences.
`masked_lm_labels`: optional masked language modeling labels: torch.LongTensor of shape [batch_size, sequence_length]
with indices selected in [-1, 0, ..., vocab_size]. All labels set to -1 are ignored (masked), the loss
is only computed for the labels set in [0, ..., vocab_size]
`next_sentence_label`: optional next sentence classification loss: torch.LongTensor of shape [batch_size]
with indices selected in [0, 1].
0 => next sentence is the continuation, 1 => next sentence is a random sentence.
Outputs:
if `masked_lm_labels` and `next_sentence_label` are not `None`:
Outputs the total_loss which is the sum of the masked language modeling loss and the next
sentence classification loss.
if `masked_lm_labels` or `next_sentence_label` is `None`:
Outputs a tuple comprising
- the masked language modeling logits of shape [batch_size, sequence_length, vocab_size], and
- the next sentence classification logits of shape [batch_size, 2].
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, 1, 0]])
config = BertConfig(vocab_size_or_config_json_file=32000, hidden_size=768,
num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072)
model = BertForPreTraining(config)
masked_lm_logits_scores, seq_relationship_logits = model(input_ids, token_type_ids, input_mask)
```
"""
def __init__(self, config):
super(BertForPreTraining, self).__init__(config)
self.bert = BertModel(config)
self.cls = BertPreTrainingHeads(config, self.bert.embeddings.word_embeddings.weight)
self.apply(self.init_bert_weights)
def forward(self, input_ids, token_type_ids=None, input_mask=None, masked_lm_labels=None,
next_sentence_label=None):
sequence_output, pooled_output = self.bert(input_ids, token_type_ids, input_mask,
output_all_encoded_layers=False)
prediction_scores, seq_relationship_score = self.cls(sequence_output, pooled_output)
if masked_lm_labels is not None and next_sentence_label is not None:
loss_fct = CrossEntropyLoss(ignore_index=-1)
masked_lm_loss = loss_fct(prediction_scores.view(-1, self.config.vocab_size), masked_lm_labels.view(-1))
next_sentence_loss = loss_fct(seq_relationship_score.view(-1, 2), next_sentence_label.view(-1))
total_loss = masked_lm_loss + next_sentence_loss
return total_loss
else:
return prediction_scores, seq_relationship_score
class BertForMaskedLM(BertPreTrainedModel):
"""BERT model with the masked language modeling head.
This module comprises the BERT model followed by the masked language modeling head.
Params:
config: a BertConfig class instance with the configuration to build a new model.
Inputs:
`input_ids`: a torch.LongTensor of shape [batch_size, sequence_length]
with the word token indices in the vocabulary(see the tokens preprocessing logic in the scripts
`extract_features.py`, `run_classifier.py` and `run_squad.py`)
`token_type_ids`: an optional torch.LongTensor of shape [batch_size, sequence_length] with the token
types indices selected in [0, 1]. Type 0 corresponds to a `sentence A` and type 1 corresponds to
a `sentence B` token (see BERT paper for more details).
`attention_mask`: an optional torch.LongTensor of shape [batch_size, sequence_length] with indices
selected in [0, 1]. It's a mask to be used if the input sequence length is smaller than the max
input sequence length in the current batch. It's the mask that we typically use for attention when
a batch has varying length sentences.
`masked_lm_labels`: masked language modeling labels: torch.LongTensor of shape [batch_size, sequence_length]
with indices selected in [-1, 0, ..., vocab_size]. All labels set to -1 are ignored (masked), the loss
is only computed for the labels set in [0, ..., vocab_size]
Outputs:
if `masked_lm_labels` is not `None`:
Outputs the masked language modeling loss.
if `masked_lm_labels` is `None`:
Outputs the masked language modeling logits of shape [batch_size, sequence_length, vocab_size].
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, 1, 0]])
config = BertConfig(vocab_size_or_config_json_file=32000, hidden_size=768,
num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072)
model = BertForMaskedLM(config)
masked_lm_logits_scores = model(input_ids, token_type_ids, input_mask)
```
"""
def __init__(self, config):
super(BertForMaskedLM, self).__init__(config)
self.bert = BertModel(config)
self.cls = BertOnlyMLMHead(config, self.bert.embeddings.word_embeddings.weight)
self.apply(self.init_bert_weights)
def forward(self, input_ids, token_type_ids=None, attention_mask=None, masked_lm_labels=None):
sequence_output, _ = self.bert(input_ids, token_type_ids, attention_mask,
output_all_encoded_layers=False)
prediction_scores = self.cls(sequence_output)
if masked_lm_labels is not None:
loss_fct = CrossEntropyLoss(ignore_index=-1)
masked_lm_loss = loss_fct(prediction_scores.view(-1, self.config.vocab_size), masked_lm_labels.view(-1))
return masked_lm_loss
else:
return prediction_scores
class BertForNextSentencePrediction(BertPreTrainedModel):
"""BERT model with next sentence prediction head.
This module comprises the BERT model followed by the next sentence classification head.
Params:
config: a BertConfig class instance with the configuration to build a new model.
Inputs:
`input_ids`: a torch.LongTensor of shape [batch_size, sequence_length]
with the word token indices in the vocabulary(see the tokens preprocessing logic in the scripts
`extract_features.py`, `run_classifier.py` and `run_squad.py`)
`token_type_ids`: an optional torch.LongTensor of shape [batch_size, sequence_length] with the token
types indices selected in [0, 1]. Type 0 corresponds to a `sentence A` and type 1 corresponds to
a `sentence B` token (see BERT paper for more details).
`attention_mask`: an optional torch.LongTensor of shape [batch_size, sequence_length] with indices
selected in [0, 1]. It's a mask to be used if the input sequence length is smaller than the max
input sequence length in the current batch. It's the mask that we typically use for attention when
a batch has varying length sentences.
`next_sentence_label`: next sentence classification loss: torch.LongTensor of shape [batch_size]
with indices selected in [0, 1].