Spaces:
Sleeping
Sleeping
File size: 11,009 Bytes
e95b4e9 |
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 |
# -*- coding: utf-8 -*-
# @Time : 2022/3/3 7:59 下午
# @Author : JianingWang
# @File : multiple_choice.py
import torch
from roformer import RoFormerPreTrainedModel, RoFormerModel
from torch import nn
from torch.nn import CrossEntropyLoss
from transformers import MegatronBertPreTrainedModel, MegatronBertModel
from transformers.modeling_outputs import MultipleChoiceModelOutput
from transformers.models.bert import BertPreTrainedModel, BertModel
class BertForTagMultipleChoice(BertPreTrainedModel):
def __init__(self, config):
super().__init__(config)
self.bert = BertModel(config)
classifier_dropout = (
config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob
)
self.dropout = nn.Dropout(classifier_dropout)
self.classifier = nn.Linear(config.hidden_size * 2, 1)
# Initialize weights and apply final processing
self.post_init()
def forward(
self,
input_ids=None,
attention_mask=None,
token_type_ids=None,
position_ids=None,
head_mask=None,
inputs_embeds=None,
labels=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
pseudo=None
):
r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See
`input_ids` above)
"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
num_choices = input_ids.shape[1] if input_ids is not None else inputs_embeds.shape[1]
input_ids = input_ids.view(-1, input_ids.size(-1)) if input_ids is not None else None
attention_mask = attention_mask.view(-1, attention_mask.size(-1)) if attention_mask is not None else None
token_type_ids = token_type_ids.view(-1, token_type_ids.size(-1)) if token_type_ids is not None else None
position_ids = position_ids.view(-1, position_ids.size(-1)) if position_ids is not None else None
inputs_embeds = (
inputs_embeds.view(-1, inputs_embeds.size(-2), inputs_embeds.size(-1))
if inputs_embeds is not None
else None
)
outputs = self.bert(
input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
position_ids=position_ids,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
w = torch.logical_and(input_ids >= min(self.config.start_token_ids), input_ids <= max(self.config.start_token_ids))
start_index = w.nonzero()[:, 1].view(-1, 2)
# <start_entity> + <end_entity> 进分类
pooled_output = torch.cat([torch.cat([x[y[0], :], x[y[1], :]]).unsqueeze(0) for x, y in zip(outputs.last_hidden_state, start_index)])
pooled_output = self.dropout(pooled_output)
logits = self.classifier(pooled_output)
reshaped_logits = logits.view(-1, num_choices)
loss = None
if labels is not None:
if pseudo is None:
loss_fct = CrossEntropyLoss()
loss = loss_fct(reshaped_logits, labels)
else:
loss_fct = CrossEntropyLoss(reduction="none")
loss = loss_fct(reshaped_logits, labels)
weight = 1 - pseudo * 0.9
loss *= weight
loss = loss.mean()
if not return_dict:
output = (reshaped_logits,) + outputs[2:]
return ((loss,) + output) if loss is not None else output
return MultipleChoiceModelOutput(
loss=loss,
logits=reshaped_logits,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)
class RoFormerForTagMultipleChoice(RoFormerPreTrainedModel):
def __init__(self, config):
super().__init__(config)
self.roformer = RoFormerModel(config, add_pooling_layer=False)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.classifier = nn.Linear(config.hidden_size * 2, 1)
# Initialize weights and apply final processing
self.post_init()
def forward(
self,
input_ids=None,
attention_mask=None,
token_type_ids=None,
head_mask=None,
inputs_embeds=None,
labels=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
):
r"""
labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
Labels for computing the multiple choice classification loss. Indices should be in ``[0, ...,
num_choices-1]`` where :obj:`num_choices` is the size of the second dimension of the input tensors. (See
:obj:`input_ids` above)
"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
num_choices = input_ids.shape[1] if input_ids is not None else inputs_embeds.shape[1]
input_ids = input_ids.view(-1, input_ids.size(-1)) if input_ids is not None else None
attention_mask = attention_mask.view(-1, attention_mask.size(-1)) if attention_mask is not None else None
token_type_ids = token_type_ids.view(-1, token_type_ids.size(-1)) if token_type_ids is not None else None
inputs_embeds = (
inputs_embeds.view(-1, inputs_embeds.size(-2), inputs_embeds.size(-1))
if inputs_embeds is not None
else None
)
outputs = self.roformer(
input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
w = torch.logical_and(input_ids >= min(self.config.start_token_ids), input_ids <= max(self.config.start_token_ids))
start_index = w.nonzero()[:, 1].view(-1, 2)
# <start_entity> + <end_entity> 进分类
pooled_output = torch.cat([torch.cat([x[y[0], :], x[y[1], :]]).unsqueeze(0) for x, y in zip(outputs.last_hidden_state, start_index)])
pooled_output = self.dropout(pooled_output)
logits = self.classifier(pooled_output)
reshaped_logits = logits.view(-1, num_choices)
loss = None
if labels is not None:
loss_fct = CrossEntropyLoss()
loss = loss_fct(reshaped_logits, labels)
if not return_dict:
output = (reshaped_logits,) + outputs[2:]
return ((loss,) + output) if loss is not None else output
return MultipleChoiceModelOutput(
loss=loss,
logits=reshaped_logits,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)
class MegatronBertForTagMultipleChoice(MegatronBertPreTrainedModel):
def __init__(self, config):
super().__init__(config)
self.bert = MegatronBertModel(config)
self.dropout = nn.Dropout(0.2)
self.classifier = nn.Linear(config.hidden_size * 2, 1)
# Initialize weights and apply final processing
self.post_init()
def forward(
self,
input_ids=None,
attention_mask=None,
token_type_ids=None,
position_ids=None,
head_mask=None,
inputs_embeds=None,
labels=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
pseudo=None
):
r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See
`input_ids` above)
"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
num_choices = input_ids.shape[1] if input_ids is not None else inputs_embeds.shape[1]
input_ids = input_ids.view(-1, input_ids.size(-1)) if input_ids is not None else None
attention_mask = attention_mask.view(-1, attention_mask.size(-1)) if attention_mask is not None else None
token_type_ids = token_type_ids.view(-1, token_type_ids.size(-1)) if token_type_ids is not None else None
position_ids = position_ids.view(-1, position_ids.size(-1)) if position_ids is not None else None
inputs_embeds = (
inputs_embeds.view(-1, inputs_embeds.size(-2), inputs_embeds.size(-1))
if inputs_embeds is not None
else None
)
outputs = self.bert(
input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
position_ids=position_ids,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
w = torch.logical_and(input_ids >= min(self.config.start_token_ids), input_ids <= max(self.config.start_token_ids))
start_index = w.nonzero()[:, 1].view(-1, 2)
# <start_entity> + <end_entity> 进分类
pooled_output = torch.cat([torch.cat([x[y[0], :], x[y[1], :]]).unsqueeze(0) for x, y in zip(outputs.last_hidden_state, start_index)])
pooled_output = self.dropout(pooled_output)
logits = self.classifier(pooled_output)
reshaped_logits = logits.view(-1, num_choices)
loss = None
if labels is not None:
if pseudo is None:
loss_fct = CrossEntropyLoss()
loss = loss_fct(reshaped_logits, labels)
else:
loss_fct = CrossEntropyLoss(reduction="none")
loss = loss_fct(reshaped_logits, labels)
weight = 1 - pseudo*0.9
loss *= weight
loss = loss.mean()
if not return_dict:
output = (reshaped_logits,) + outputs[2:]
return ((loss,) + output) if loss is not None else output
return MultipleChoiceModelOutput(
loss=loss,
logits=reshaped_logits,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)
|