File size: 12,242 Bytes
3f75218
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# ------------------------------------------------------------------------
# Grounding DINO
# url: https://github.com/IDEA-Research/GroundingDINO
# Copyright (c) 2023 IDEA. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------

import torch
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
from torch import Tensor, nn
from torchvision.ops.boxes import nms
from transformers import BertConfig, BertModel, BertPreTrainedModel
from transformers.modeling_outputs import BaseModelOutputWithPoolingAndCrossAttentions


class BertModelWarper(nn.Module):
    def __init__(self, bert_model):
        super().__init__()
        # self.bert = bert_modelc

        self.config = bert_model.config
        self.embeddings = bert_model.embeddings
        self.encoder = bert_model.encoder
        self.pooler = bert_model.pooler

        self.get_extended_attention_mask = bert_model.get_extended_attention_mask
        self.invert_attention_mask = bert_model.invert_attention_mask
        self.get_head_mask = bert_model.get_head_mask

    def forward(
        self,
        input_ids=None,
        attention_mask=None,
        token_type_ids=None,
        position_ids=None,
        head_mask=None,
        inputs_embeds=None,
        encoder_hidden_states=None,
        encoder_attention_mask=None,
        past_key_values=None,
        use_cache=None,
        output_attentions=None,
        output_hidden_states=None,
        return_dict=None,
    ):
        r"""
        encoder_hidden_states  (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
            Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
            the model is configured as a decoder.
        encoder_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
            Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
            the cross-attention if the model is configured as a decoder. Mask values selected in ``[0, 1]``:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.
        past_key_values (:obj:`tuple(tuple(torch.FloatTensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
            Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.

            If :obj:`past_key_values` are used, the user can optionally input only the last :obj:`decoder_input_ids`
            (those that don't have their past key value states given to this model) of shape :obj:`(batch_size, 1)`
            instead of all :obj:`decoder_input_ids` of shape :obj:`(batch_size, sequence_length)`.
        use_cache (:obj:`bool`, `optional`):
            If set to :obj:`True`, :obj:`past_key_values` key value states are returned and can be used to speed up
            decoding (see :obj:`past_key_values`).
        """
        output_attentions = (
            output_attentions if output_attentions is not None else self.config.output_attentions
        )
        output_hidden_states = (
            output_hidden_states
            if output_hidden_states is not None
            else self.config.output_hidden_states
        )
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if self.config.is_decoder:
            use_cache = use_cache if use_cache is not None else self.config.use_cache
        else:
            use_cache = False

        if input_ids is not None and inputs_embeds is not None:
            raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
        elif input_ids is not None:
            input_shape = input_ids.size()
            batch_size, seq_length = input_shape
        elif inputs_embeds is not None:
            input_shape = inputs_embeds.size()[:-1]
            batch_size, seq_length = input_shape
        else:
            raise ValueError("You have to specify either input_ids or inputs_embeds")

        device = input_ids.device if input_ids is not None else inputs_embeds.device

        # past_key_values_length
        past_key_values_length = (
            past_key_values[0][0].shape[2] if past_key_values is not None else 0
        )

        if attention_mask is None:
            attention_mask = torch.ones(
                ((batch_size, seq_length + past_key_values_length)), device=device
            )
        if token_type_ids is None:
            token_type_ids = torch.zeros(input_shape, dtype=torch.long, device=device)

        # We can provide a self-attention mask of dimensions [batch_size, from_seq_length, to_seq_length]
        # ourselves in which case we just need to make it broadcastable to all heads.
        extended_attention_mask: torch.Tensor = self.get_extended_attention_mask(
            attention_mask, input_shape, device
        )

        # If a 2D or 3D attention mask is provided for the cross-attention
        # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
        if self.config.is_decoder and encoder_hidden_states is not None:
            encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.size()
            encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
            if encoder_attention_mask is None:
                encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device)
            encoder_extended_attention_mask = self.invert_attention_mask(encoder_attention_mask)
        else:
            encoder_extended_attention_mask = None
        # if os.environ.get('IPDB_SHILONG_DEBUG', None) == 'INFO':
        #     import ipdb; ipdb.set_trace()

        # Prepare head mask if needed
        # 1.0 in head_mask indicate we keep the head
        # attention_probs has shape bsz x n_heads x N x N
        # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
        # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
        head_mask = self.get_head_mask(head_mask, self.config.num_hidden_layers)

        embedding_output = self.embeddings(
            input_ids=input_ids,
            position_ids=position_ids,
            token_type_ids=token_type_ids,
            inputs_embeds=inputs_embeds,
            past_key_values_length=past_key_values_length,
        )

        encoder_outputs = self.encoder(
            embedding_output,
            attention_mask=extended_attention_mask,
            head_mask=head_mask,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_extended_attention_mask,
            past_key_values=past_key_values,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        sequence_output = encoder_outputs[0]
        pooled_output = self.pooler(sequence_output) if self.pooler is not None else None

        if not return_dict:
            return (sequence_output, pooled_output) + encoder_outputs[1:]

        return BaseModelOutputWithPoolingAndCrossAttentions(
            last_hidden_state=sequence_output,
            pooler_output=pooled_output,
            past_key_values=encoder_outputs.past_key_values,
            hidden_states=encoder_outputs.hidden_states,
            attentions=encoder_outputs.attentions,
            cross_attentions=encoder_outputs.cross_attentions,
        )


class TextEncoderShell(nn.Module):
    def __init__(self, text_encoder):
        super().__init__()
        self.text_encoder = text_encoder
        self.config = self.text_encoder.config

    def forward(self, **kw):
        # feed into text encoder
        return self.text_encoder(**kw)


def generate_masks_with_special_tokens(tokenized, special_tokens_list, tokenizer):
    """Generate attention mask between each pair of special tokens
    Args:
        input_ids (torch.Tensor): input ids. Shape: [bs, num_token]
        special_tokens_mask (list): special tokens mask.
    Returns:
        torch.Tensor: attention mask between each special tokens.
    """
    input_ids = tokenized["input_ids"]
    bs, num_token = input_ids.shape
    # special_tokens_mask: bs, num_token. 1 for special tokens. 0 for normal tokens
    special_tokens_mask = torch.zeros((bs, num_token), device=input_ids.device).bool()
    for special_token in special_tokens_list:
        special_tokens_mask |= input_ids == special_token

    # idxs: each row is a list of indices of special tokens
    idxs = torch.nonzero(special_tokens_mask)

    # generate attention mask and positional ids
    attention_mask = (
        torch.eye(num_token, device=input_ids.device).bool().unsqueeze(0).repeat(bs, 1, 1)
    )
    position_ids = torch.zeros((bs, num_token), device=input_ids.device)
    previous_col = 0
    for i in range(idxs.shape[0]):
        row, col = idxs[i]
        if (col == 0) or (col == num_token - 1):
            attention_mask[row, col, col] = True
            position_ids[row, col] = 0
        else:
            attention_mask[row, previous_col + 1 : col + 1, previous_col + 1 : col + 1] = True
            position_ids[row, previous_col + 1 : col + 1] = torch.arange(
                0, col - previous_col, device=input_ids.device
            )

        previous_col = col

    # # padding mask
    # padding_mask = tokenized['attention_mask']
    # attention_mask = attention_mask & padding_mask.unsqueeze(1).bool() & padding_mask.unsqueeze(2).bool()

    return attention_mask, position_ids.to(torch.long)


def generate_masks_with_special_tokens_and_transfer_map(tokenized, special_tokens_list, tokenizer):
    """Generate attention mask between each pair of special tokens
    Args:
        input_ids (torch.Tensor): input ids. Shape: [bs, num_token]
        special_tokens_mask (list): special tokens mask.
    Returns:
        torch.Tensor: attention mask between each special tokens.
    """
    input_ids = tokenized["input_ids"]
    bs, num_token = input_ids.shape
    # special_tokens_mask: bs, num_token. 1 for special tokens. 0 for normal tokens
    special_tokens_mask = torch.zeros((bs, num_token), device=input_ids.device).bool()
    for special_token in special_tokens_list:
        special_tokens_mask |= input_ids == special_token

    # idxs: each row is a list of indices of special tokens
    idxs = torch.nonzero(special_tokens_mask)

    # generate attention mask and positional ids
    attention_mask = (
        torch.eye(num_token, device=input_ids.device).bool().unsqueeze(0).repeat(bs, 1, 1)
    )
    position_ids = torch.zeros((bs, num_token), device=input_ids.device)
    cate_to_token_mask_list = [[] for _ in range(bs)]
    previous_col = 0
    for i in range(idxs.shape[0]):
        row, col = idxs[i]
        if (col == 0) or (col == num_token - 1):
            attention_mask[row, col, col] = True
            position_ids[row, col] = 0
        else:
            attention_mask[row, previous_col + 1 : col + 1, previous_col + 1 : col + 1] = True
            position_ids[row, previous_col + 1 : col + 1] = torch.arange(
                0, col - previous_col, device=input_ids.device
            )
            c2t_maski = torch.zeros((num_token), device=input_ids.device).bool()
            c2t_maski[previous_col + 1 : col] = True
            cate_to_token_mask_list[row].append(c2t_maski)
        previous_col = col

    cate_to_token_mask_list = [
        torch.stack(cate_to_token_mask_listi, dim=0)
        for cate_to_token_mask_listi in cate_to_token_mask_list
    ]

    # # padding mask
    # padding_mask = tokenized['attention_mask']
    # attention_mask = attention_mask & padding_mask.unsqueeze(1).bool() & padding_mask.unsqueeze(2).bool()

    return attention_mask, position_ids.to(torch.long), cate_to_token_mask_list