forked from HUSTAI/uie_pytorch
-
Notifications
You must be signed in to change notification settings - Fork 0
/
model.py
306 lines (280 loc) · 16.1 KB
/
model.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
# Copyright (c) 2022 Heiheiyoyo. 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:https://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.
import torch
import torch.nn as nn
from dataclasses import dataclass
from transformers import PretrainedConfig
from transformers.utils import ModelOutput
from typing import Optional, Tuple
from ernie import ErnieModel, ErniePreTrainedModel
from ernie_m import ErnieMModel, ErnieMPreTrainedModel
@dataclass
class UIEModelOutput(ModelOutput):
"""
Output class for outputs of UIE.
Args:
loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.
start_prob (`torch.FloatTensor` of shape `(batch_size, sequence_length)`):
Span-start scores (after Sigmoid).
end_prob (`torch.FloatTensor` of shape `(batch_size, sequence_length)`):
Span-end scores (after Sigmoid).
hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `torch.FloatTensor` (one for each layer) of shape `(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.
"""
loss: Optional[torch.FloatTensor] = None
start_prob: torch.FloatTensor = None
end_prob: torch.FloatTensor = None
hidden_states: Optional[Tuple[torch.FloatTensor]] = None
attentions: Optional[Tuple[torch.FloatTensor]] = None
class UIE(ErniePreTrainedModel):
"""
UIE model based on Bert model.
This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the
library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
etc.)
This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
and behavior.
Parameters:
config ([`PretrainedConfig`]): Model configuration class with all the parameters of the model.
Initializing with a config file does not load the weights associated with the model, only the
configuration. Check out the [`~PreTrainedModel.from_pretrained`] method to load the model weights.
"""
def __init__(self, config: PretrainedConfig):
super(UIE, self).__init__(config)
self.encoder = ErnieModel(config)
self.config = config
hidden_size = self.config.hidden_size
self.linear_start = nn.Linear(hidden_size, 1)
self.linear_end = nn.Linear(hidden_size, 1)
self.sigmoid = nn.Sigmoid()
# if hasattr(config, 'use_task_id') and config.use_task_id:
# # Add task type embedding to BERT
# task_type_embeddings = nn.Embedding(
# config.task_type_vocab_size, config.hidden_size)
# self.encoder.embeddings.task_type_embeddings = task_type_embeddings
# def hook(module, input, output):
# input = input[0]
# return output+task_type_embeddings(torch.zeros(input.size(), dtype=torch.int64, device=input.device))
# self.encoder.embeddings.word_embeddings.register_forward_hook(hook)
self.post_init()
def forward(self, input_ids: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.Tensor] = None,
position_ids: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
head_mask: Optional[torch.Tensor] = None,
inputs_embeds: Optional[torch.Tensor] = None,
start_positions: Optional[torch.Tensor] = None,
end_positions: Optional[torch.Tensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None
):
"""
Args:
input_ids (`torch.LongTensor` of shape `({0})`):
Indices of input sequence tokens in the vocabulary.
Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.encode`] and
[`PreTrainedTokenizer.__call__`] for details.
[What are input IDs?](../glossary#input-ids)
attention_mask (`torch.FloatTensor` of shape `({0})`, *optional*):
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
- 1 for tokens that are **not masked**,
- 0 for tokens that are **masked**.
[What are attention masks?](../glossary#attention-mask)
token_type_ids (`torch.LongTensor` of shape `({0})`, *optional*):
Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0,
1]`:
- 0 corresponds to a *sentence A* token,
- 1 corresponds to a *sentence B* token.
[What are token type IDs?](../glossary#token-type-ids)
position_ids (`torch.LongTensor` of shape `({0})`, *optional*):
Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
config.max_position_embeddings - 1]`.
[What are position IDs?](../glossary#position-ids)
head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
- 1 indicates the head is **not masked**,
- 0 indicates the head is **masked**.
inputs_embeds (`torch.FloatTensor` of shape `({0}, hidden_size)`, *optional*):
Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
model's internal embedding lookup matrix.
start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for position (index) of the start of the labelled span for computing the token classification loss.
Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
are not taken into account for computing the loss.
end_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for position (index) of the end of the labelled span for computing the token classification loss.
Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
are not taken into account for computing the loss.
output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail.
output_hidden_states (`bool`, *optional*):
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
more detail.
return_dict (`bool`, *optional*):
Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
outputs = self.encoder(
input_ids=input_ids,
token_type_ids=token_type_ids,
position_ids=position_ids,
attention_mask=attention_mask,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict
)
sequence_output = outputs[0]
start_logits = self.linear_start(sequence_output)
start_logits = torch.squeeze(start_logits, -1)
start_prob = self.sigmoid(start_logits)
end_logits = self.linear_end(sequence_output)
end_logits = torch.squeeze(end_logits, -1)
end_prob = self.sigmoid(end_logits)
total_loss = None
if start_positions is not None and end_positions is not None:
loss_fct = nn.BCELoss()
start_loss = loss_fct(start_prob, start_positions)
end_loss = loss_fct(end_prob, end_positions)
total_loss = (start_loss + end_loss) / 2.0
if not return_dict:
output = (start_prob, end_prob) + outputs[2:]
return ((total_loss,) + output) if total_loss is not None else output
return UIEModelOutput(
loss=total_loss,
start_prob=start_prob,
end_prob=end_prob,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)
class UIEM(ErnieMPreTrainedModel):
"""
UIE model based on Bert model.
This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the
library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
etc.)
This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
and behavior.
Parameters:
config ([`PretrainedConfig`]): Model configuration class with all the parameters of the model.
Initializing with a config file does not load the weights associated with the model, only the
configuration. Check out the [`~PreTrainedModel.from_pretrained`] method to load the model weights.
"""
def __init__(self, config: PretrainedConfig):
super(UIEM, self).__init__(config)
self.encoder = ErnieMModel(config)
self.config = config
hidden_size = self.config.hidden_size
self.linear_start = nn.Linear(hidden_size, 1)
self.linear_end = nn.Linear(hidden_size, 1)
self.sigmoid = nn.Sigmoid()
self.post_init()
def forward(self, input_ids: Optional[torch.Tensor] = None,
position_ids: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
head_mask: Optional[torch.Tensor] = None,
start_positions: Optional[torch.Tensor] = None,
end_positions: Optional[torch.Tensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None
):
"""
Args:
input_ids (`torch.LongTensor` of shape `({0})`):
Indices of input sequence tokens in the vocabulary.
Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.encode`] and
[`PreTrainedTokenizer.__call__`] for details.
[What are input IDs?](../glossary#input-ids)
attention_mask (`torch.FloatTensor` of shape `({0})`, *optional*):
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
- 1 for tokens that are **not masked**,
- 0 for tokens that are **masked**.
[What are attention masks?](../glossary#attention-mask)
position_ids (`torch.LongTensor` of shape `({0})`, *optional*):
Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
config.max_position_embeddings - 1]`.
[What are position IDs?](../glossary#position-ids)
head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
- 1 indicates the head is **not masked**,
- 0 indicates the head is **masked**.
inputs_embeds (`torch.FloatTensor` of shape `({0}, hidden_size)`, *optional*):
Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
model's internal embedding lookup matrix.
start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for position (index) of the start of the labelled span for computing the token classification loss.
Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
are not taken into account for computing the loss.
end_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for position (index) of the end of the labelled span for computing the token classification loss.
Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
are not taken into account for computing the loss.
output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail.
output_hidden_states (`bool`, *optional*):
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
more detail.
return_dict (`bool`, *optional*):
Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
outputs = self.encoder(
input_ids=input_ids,
position_ids=position_ids,
# attention_mask=attention_mask,
# head_mask=head_mask,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict
)
sequence_output = outputs[0]
start_logits = self.linear_start(sequence_output)
start_logits = torch.squeeze(start_logits, -1)
start_prob = self.sigmoid(start_logits)
end_logits = self.linear_end(sequence_output)
end_logits = torch.squeeze(end_logits, -1)
end_prob = self.sigmoid(end_logits)
total_loss = None
if start_positions is not None and end_positions is not None:
loss_fct = nn.BCELoss()
start_loss = loss_fct(start_prob, start_positions)
end_loss = loss_fct(end_prob, end_positions)
total_loss = (start_loss + end_loss) / 2.0
if not return_dict:
output = (start_prob, end_prob) + outputs[2:]
return ((total_loss,) + output) if total_loss is not None else output
return UIEModelOutput(
loss=total_loss,
start_prob=start_prob,
end_prob=end_prob,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)