ai-content-maker/.venv/Lib/site-packages/transformers/models/markuplm/modeling_markuplm.py

1317 lines
57 KiB
Python

# coding=utf-8
# Copyright 2022 Microsoft Research Asia and the HuggingFace Inc. team.
#
# 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 MarkupLM model."""
import math
import os
from typing import Optional, Tuple, Union
import torch
import torch.utils.checkpoint
from torch import nn
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
from ...activations import ACT2FN
from ...file_utils import (
add_start_docstrings,
add_start_docstrings_to_model_forward,
replace_return_docstrings,
)
from ...modeling_outputs import (
BaseModelOutputWithPastAndCrossAttentions,
BaseModelOutputWithPoolingAndCrossAttentions,
MaskedLMOutput,
QuestionAnsweringModelOutput,
SequenceClassifierOutput,
TokenClassifierOutput,
)
from ...modeling_utils import (
PreTrainedModel,
apply_chunking_to_forward,
find_pruneable_heads_and_indices,
prune_linear_layer,
)
from ...utils import logging
from .configuration_markuplm import MarkupLMConfig
logger = logging.get_logger(__name__)
_CHECKPOINT_FOR_DOC = "microsoft/markuplm-base"
_CONFIG_FOR_DOC = "MarkupLMConfig"
from ..deprecated._archive_maps import MARKUPLM_PRETRAINED_MODEL_ARCHIVE_LIST # noqa: F401, E402
class XPathEmbeddings(nn.Module):
"""Construct the embeddings from xpath tags and subscripts.
We drop tree-id in this version, as its info can be covered by xpath.
"""
def __init__(self, config):
super(XPathEmbeddings, self).__init__()
self.max_depth = config.max_depth
self.xpath_unitseq2_embeddings = nn.Linear(config.xpath_unit_hidden_size * self.max_depth, config.hidden_size)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.activation = nn.ReLU()
self.xpath_unitseq2_inner = nn.Linear(config.xpath_unit_hidden_size * self.max_depth, 4 * config.hidden_size)
self.inner2emb = nn.Linear(4 * config.hidden_size, config.hidden_size)
self.xpath_tag_sub_embeddings = nn.ModuleList(
[
nn.Embedding(config.max_xpath_tag_unit_embeddings, config.xpath_unit_hidden_size)
for _ in range(self.max_depth)
]
)
self.xpath_subs_sub_embeddings = nn.ModuleList(
[
nn.Embedding(config.max_xpath_subs_unit_embeddings, config.xpath_unit_hidden_size)
for _ in range(self.max_depth)
]
)
def forward(self, xpath_tags_seq=None, xpath_subs_seq=None):
xpath_tags_embeddings = []
xpath_subs_embeddings = []
for i in range(self.max_depth):
xpath_tags_embeddings.append(self.xpath_tag_sub_embeddings[i](xpath_tags_seq[:, :, i]))
xpath_subs_embeddings.append(self.xpath_subs_sub_embeddings[i](xpath_subs_seq[:, :, i]))
xpath_tags_embeddings = torch.cat(xpath_tags_embeddings, dim=-1)
xpath_subs_embeddings = torch.cat(xpath_subs_embeddings, dim=-1)
xpath_embeddings = xpath_tags_embeddings + xpath_subs_embeddings
xpath_embeddings = self.inner2emb(self.dropout(self.activation(self.xpath_unitseq2_inner(xpath_embeddings))))
return xpath_embeddings
# Copied from transformers.models.roberta.modeling_roberta.create_position_ids_from_input_ids
def create_position_ids_from_input_ids(input_ids, padding_idx, past_key_values_length=0):
"""
Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding symbols
are ignored. This is modified from fairseq's `utils.make_positions`.
Args:
x: torch.Tensor x:
Returns: torch.Tensor
"""
# The series of casts and type-conversions here are carefully balanced to both work with ONNX export and XLA.
mask = input_ids.ne(padding_idx).int()
incremental_indices = (torch.cumsum(mask, dim=1).type_as(mask) + past_key_values_length) * mask
return incremental_indices.long() + padding_idx
class MarkupLMEmbeddings(nn.Module):
"""Construct the embeddings from word, position and token_type embeddings."""
def __init__(self, config):
super(MarkupLMEmbeddings, self).__init__()
self.config = config
self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=config.pad_token_id)
self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size)
self.max_depth = config.max_depth
self.xpath_embeddings = XPathEmbeddings(config)
self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size)
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.register_buffer(
"position_ids", torch.arange(config.max_position_embeddings).expand((1, -1)), persistent=False
)
self.padding_idx = config.pad_token_id
self.position_embeddings = nn.Embedding(
config.max_position_embeddings, config.hidden_size, padding_idx=self.padding_idx
)
# Copied from transformers.models.roberta.modeling_roberta.RobertaEmbeddings.create_position_ids_from_inputs_embeds
def create_position_ids_from_inputs_embeds(self, inputs_embeds):
"""
We are provided embeddings directly. We cannot infer which are padded so just generate sequential position ids.
Args:
inputs_embeds: torch.Tensor
Returns: torch.Tensor
"""
input_shape = inputs_embeds.size()[:-1]
sequence_length = input_shape[1]
position_ids = torch.arange(
self.padding_idx + 1, sequence_length + self.padding_idx + 1, dtype=torch.long, device=inputs_embeds.device
)
return position_ids.unsqueeze(0).expand(input_shape)
def forward(
self,
input_ids=None,
xpath_tags_seq=None,
xpath_subs_seq=None,
token_type_ids=None,
position_ids=None,
inputs_embeds=None,
past_key_values_length=0,
):
if input_ids is not None:
input_shape = input_ids.size()
else:
input_shape = inputs_embeds.size()[:-1]
device = input_ids.device if input_ids is not None else inputs_embeds.device
if position_ids is None:
if input_ids is not None:
# Create the position ids from the input token ids. Any padded tokens remain padded.
position_ids = create_position_ids_from_input_ids(input_ids, self.padding_idx, past_key_values_length)
else:
position_ids = self.create_position_ids_from_inputs_embeds(inputs_embeds)
if token_type_ids is None:
token_type_ids = torch.zeros(input_shape, dtype=torch.long, device=device)
if inputs_embeds is None:
inputs_embeds = self.word_embeddings(input_ids)
# prepare xpath seq
if xpath_tags_seq is None:
xpath_tags_seq = self.config.tag_pad_id * torch.ones(
tuple(list(input_shape) + [self.max_depth]), dtype=torch.long, device=device
)
if xpath_subs_seq is None:
xpath_subs_seq = self.config.subs_pad_id * torch.ones(
tuple(list(input_shape) + [self.max_depth]), dtype=torch.long, device=device
)
words_embeddings = inputs_embeds
position_embeddings = self.position_embeddings(position_ids)
token_type_embeddings = self.token_type_embeddings(token_type_ids)
xpath_embeddings = self.xpath_embeddings(xpath_tags_seq, xpath_subs_seq)
embeddings = words_embeddings + position_embeddings + token_type_embeddings + xpath_embeddings
embeddings = self.LayerNorm(embeddings)
embeddings = self.dropout(embeddings)
return embeddings
# Copied from transformers.models.bert.modeling_bert.BertSelfOutput with Bert->MarkupLM
class MarkupLMSelfOutput(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
def forward(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor:
hidden_states = self.dense(hidden_states)
hidden_states = self.dropout(hidden_states)
hidden_states = self.LayerNorm(hidden_states + input_tensor)
return hidden_states
# Copied from transformers.models.bert.modeling_bert.BertIntermediate
class MarkupLMIntermediate(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.hidden_size, config.intermediate_size)
if isinstance(config.hidden_act, str):
self.intermediate_act_fn = ACT2FN[config.hidden_act]
else:
self.intermediate_act_fn = config.hidden_act
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
hidden_states = self.dense(hidden_states)
hidden_states = self.intermediate_act_fn(hidden_states)
return hidden_states
# Copied from transformers.models.bert.modeling_bert.BertOutput with Bert->MarkupLM
class MarkupLMOutput(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.intermediate_size, config.hidden_size)
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
def forward(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor:
hidden_states = self.dense(hidden_states)
hidden_states = self.dropout(hidden_states)
hidden_states = self.LayerNorm(hidden_states + input_tensor)
return hidden_states
# Copied from transformers.models.bert.modeling_bert.BertPooler
class MarkupLMPooler(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
self.activation = nn.Tanh()
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
# 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
# Copied from transformers.models.bert.modeling_bert.BertPredictionHeadTransform with Bert->MarkupLM
class MarkupLMPredictionHeadTransform(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
if isinstance(config.hidden_act, str):
self.transform_act_fn = ACT2FN[config.hidden_act]
else:
self.transform_act_fn = config.hidden_act
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
hidden_states = self.dense(hidden_states)
hidden_states = self.transform_act_fn(hidden_states)
hidden_states = self.LayerNorm(hidden_states)
return hidden_states
# Copied from transformers.models.bert.modeling_bert.BertLMPredictionHead with Bert->MarkupLM
class MarkupLMLMPredictionHead(nn.Module):
def __init__(self, config):
super().__init__()
self.transform = MarkupLMPredictionHeadTransform(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(config.hidden_size, config.vocab_size, bias=False)
self.bias = nn.Parameter(torch.zeros(config.vocab_size))
# Need a link between the two variables so that the bias is correctly resized with `resize_token_embeddings`
self.decoder.bias = self.bias
def forward(self, hidden_states):
hidden_states = self.transform(hidden_states)
hidden_states = self.decoder(hidden_states)
return hidden_states
# Copied from transformers.models.bert.modeling_bert.BertOnlyMLMHead with Bert->MarkupLM
class MarkupLMOnlyMLMHead(nn.Module):
def __init__(self, config):
super().__init__()
self.predictions = MarkupLMLMPredictionHead(config)
def forward(self, sequence_output: torch.Tensor) -> torch.Tensor:
prediction_scores = self.predictions(sequence_output)
return prediction_scores
# Copied from transformers.models.bert.modeling_bert.BertSelfAttention with Bert->MarkupLM
class MarkupLMSelfAttention(nn.Module):
def __init__(self, config, position_embedding_type=None):
super().__init__()
if config.hidden_size % config.num_attention_heads != 0 and not hasattr(config, "embedding_size"):
raise ValueError(
f"The hidden size ({config.hidden_size}) is not a multiple of the number of attention "
f"heads ({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)
self.position_embedding_type = position_embedding_type or getattr(
config, "position_embedding_type", "absolute"
)
if self.position_embedding_type == "relative_key" or self.position_embedding_type == "relative_key_query":
self.max_position_embeddings = config.max_position_embeddings
self.distance_embedding = nn.Embedding(2 * config.max_position_embeddings - 1, self.attention_head_size)
self.is_decoder = config.is_decoder
def transpose_for_scores(self, x: torch.Tensor) -> torch.Tensor:
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: torch.Tensor,
attention_mask: Optional[torch.FloatTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
output_attentions: Optional[bool] = False,
) -> Tuple[torch.Tensor]:
mixed_query_layer = self.query(hidden_states)
# If this is instantiated as a cross-attention module, the keys
# and values come from an encoder; the attention mask needs to be
# such that the encoder's padding tokens are not attended to.
is_cross_attention = encoder_hidden_states is not None
if is_cross_attention and past_key_value is not None:
# reuse k,v, cross_attentions
key_layer = past_key_value[0]
value_layer = past_key_value[1]
attention_mask = encoder_attention_mask
elif is_cross_attention:
key_layer = self.transpose_for_scores(self.key(encoder_hidden_states))
value_layer = self.transpose_for_scores(self.value(encoder_hidden_states))
attention_mask = encoder_attention_mask
elif past_key_value is not None:
key_layer = self.transpose_for_scores(self.key(hidden_states))
value_layer = self.transpose_for_scores(self.value(hidden_states))
key_layer = torch.cat([past_key_value[0], key_layer], dim=2)
value_layer = torch.cat([past_key_value[1], value_layer], dim=2)
else:
key_layer = self.transpose_for_scores(self.key(hidden_states))
value_layer = self.transpose_for_scores(self.value(hidden_states))
query_layer = self.transpose_for_scores(mixed_query_layer)
use_cache = past_key_value is not None
if self.is_decoder:
# if cross_attention save Tuple(torch.Tensor, torch.Tensor) of all cross attention key/value_states.
# Further calls to cross_attention layer can then reuse all cross-attention
# key/value_states (first "if" case)
# if uni-directional self-attention (decoder) save Tuple(torch.Tensor, torch.Tensor) of
# all previous decoder key/value_states. Further calls to uni-directional self-attention
# can concat previous decoder key/value_states to current projected key/value_states (third "elif" case)
# if encoder bi-directional self-attention `past_key_value` is always `None`
past_key_value = (key_layer, 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))
if self.position_embedding_type == "relative_key" or self.position_embedding_type == "relative_key_query":
query_length, key_length = query_layer.shape[2], key_layer.shape[2]
if use_cache:
position_ids_l = torch.tensor(key_length - 1, dtype=torch.long, device=hidden_states.device).view(
-1, 1
)
else:
position_ids_l = torch.arange(query_length, dtype=torch.long, device=hidden_states.device).view(-1, 1)
position_ids_r = torch.arange(key_length, dtype=torch.long, device=hidden_states.device).view(1, -1)
distance = position_ids_l - position_ids_r
positional_embedding = self.distance_embedding(distance + self.max_position_embeddings - 1)
positional_embedding = positional_embedding.to(dtype=query_layer.dtype) # fp16 compatibility
if self.position_embedding_type == "relative_key":
relative_position_scores = torch.einsum("bhld,lrd->bhlr", query_layer, positional_embedding)
attention_scores = attention_scores + relative_position_scores
elif self.position_embedding_type == "relative_key_query":
relative_position_scores_query = torch.einsum("bhld,lrd->bhlr", query_layer, positional_embedding)
relative_position_scores_key = torch.einsum("bhrd,lrd->bhlr", key_layer, positional_embedding)
attention_scores = attention_scores + relative_position_scores_query + relative_position_scores_key
attention_scores = attention_scores / math.sqrt(self.attention_head_size)
if attention_mask is not None:
# Apply the attention mask is (precomputed for all layers in MarkupLMModel forward() function)
attention_scores = attention_scores + attention_mask
# Normalize the attention scores to probabilities.
attention_probs = nn.functional.softmax(attention_scores, dim=-1)
# 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)
# Mask heads if we want to
if head_mask is not None:
attention_probs = attention_probs * head_mask
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,)
if self.is_decoder:
outputs = outputs + (past_key_value,)
return outputs
# Copied from transformers.models.bert.modeling_bert.BertAttention with Bert->MarkupLM
class MarkupLMAttention(nn.Module):
def __init__(self, config, position_embedding_type=None):
super().__init__()
self.self = MarkupLMSelfAttention(config, position_embedding_type=position_embedding_type)
self.output = MarkupLMSelfOutput(config)
self.pruned_heads = set()
def prune_heads(self, heads):
if len(heads) == 0:
return
heads, index = find_pruneable_heads_and_indices(
heads, self.self.num_attention_heads, self.self.attention_head_size, self.pruned_heads
)
# Prune linear layers
self.self.query = prune_linear_layer(self.self.query, index)
self.self.key = prune_linear_layer(self.self.key, index)
self.self.value = prune_linear_layer(self.self.value, index)
self.output.dense = prune_linear_layer(self.output.dense, index, dim=1)
# Update hyper params and store pruned heads
self.self.num_attention_heads = self.self.num_attention_heads - len(heads)
self.self.all_head_size = self.self.attention_head_size * self.self.num_attention_heads
self.pruned_heads = self.pruned_heads.union(heads)
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.FloatTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
output_attentions: Optional[bool] = False,
) -> Tuple[torch.Tensor]:
self_outputs = self.self(
hidden_states,
attention_mask,
head_mask,
encoder_hidden_states,
encoder_attention_mask,
past_key_value,
output_attentions,
)
attention_output = self.output(self_outputs[0], hidden_states)
outputs = (attention_output,) + self_outputs[1:] # add attentions if we output them
return outputs
# Copied from transformers.models.bert.modeling_bert.BertLayer with Bert->MarkupLM
class MarkupLMLayer(nn.Module):
def __init__(self, config):
super().__init__()
self.chunk_size_feed_forward = config.chunk_size_feed_forward
self.seq_len_dim = 1
self.attention = MarkupLMAttention(config)
self.is_decoder = config.is_decoder
self.add_cross_attention = config.add_cross_attention
if self.add_cross_attention:
if not self.is_decoder:
raise ValueError(f"{self} should be used as a decoder model if cross attention is added")
self.crossattention = MarkupLMAttention(config, position_embedding_type="absolute")
self.intermediate = MarkupLMIntermediate(config)
self.output = MarkupLMOutput(config)
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.FloatTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
output_attentions: Optional[bool] = False,
) -> Tuple[torch.Tensor]:
# decoder uni-directional self-attention cached key/values tuple is at positions 1,2
self_attn_past_key_value = past_key_value[:2] if past_key_value is not None else None
self_attention_outputs = self.attention(
hidden_states,
attention_mask,
head_mask,
output_attentions=output_attentions,
past_key_value=self_attn_past_key_value,
)
attention_output = self_attention_outputs[0]
# if decoder, the last output is tuple of self-attn cache
if self.is_decoder:
outputs = self_attention_outputs[1:-1]
present_key_value = self_attention_outputs[-1]
else:
outputs = self_attention_outputs[1:] # add self attentions if we output attention weights
cross_attn_present_key_value = None
if self.is_decoder and encoder_hidden_states is not None:
if not hasattr(self, "crossattention"):
raise ValueError(
f"If `encoder_hidden_states` are passed, {self} has to be instantiated with cross-attention layers"
" by setting `config.add_cross_attention=True`"
)
# cross_attn cached key/values tuple is at positions 3,4 of past_key_value tuple
cross_attn_past_key_value = past_key_value[-2:] if past_key_value is not None else None
cross_attention_outputs = self.crossattention(
attention_output,
attention_mask,
head_mask,
encoder_hidden_states,
encoder_attention_mask,
cross_attn_past_key_value,
output_attentions,
)
attention_output = cross_attention_outputs[0]
outputs = outputs + cross_attention_outputs[1:-1] # add cross attentions if we output attention weights
# add cross-attn cache to positions 3,4 of present_key_value tuple
cross_attn_present_key_value = cross_attention_outputs[-1]
present_key_value = present_key_value + cross_attn_present_key_value
layer_output = apply_chunking_to_forward(
self.feed_forward_chunk, self.chunk_size_feed_forward, self.seq_len_dim, attention_output
)
outputs = (layer_output,) + outputs
# if decoder, return the attn key/values as the last output
if self.is_decoder:
outputs = outputs + (present_key_value,)
return outputs
def feed_forward_chunk(self, attention_output):
intermediate_output = self.intermediate(attention_output)
layer_output = self.output(intermediate_output, attention_output)
return layer_output
# Copied from transformers.models.bert.modeling_bert.BertEncoder with Bert->MarkupLM
class MarkupLMEncoder(nn.Module):
def __init__(self, config):
super().__init__()
self.config = config
self.layer = nn.ModuleList([MarkupLMLayer(config) for _ in range(config.num_hidden_layers)])
self.gradient_checkpointing = False
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.FloatTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
use_cache: Optional[bool] = None,
output_attentions: Optional[bool] = False,
output_hidden_states: Optional[bool] = False,
return_dict: Optional[bool] = True,
) -> Union[Tuple[torch.Tensor], BaseModelOutputWithPastAndCrossAttentions]:
all_hidden_states = () if output_hidden_states else None
all_self_attentions = () if output_attentions else None
all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None
if self.gradient_checkpointing and self.training:
if use_cache:
logger.warning_once(
"`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
)
use_cache = False
next_decoder_cache = () if use_cache else None
for i, layer_module in enumerate(self.layer):
if output_hidden_states:
all_hidden_states = all_hidden_states + (hidden_states,)
layer_head_mask = head_mask[i] if head_mask is not None else None
past_key_value = past_key_values[i] if past_key_values is not None else None
if self.gradient_checkpointing and self.training:
layer_outputs = self._gradient_checkpointing_func(
layer_module.__call__,
hidden_states,
attention_mask,
layer_head_mask,
encoder_hidden_states,
encoder_attention_mask,
past_key_value,
output_attentions,
)
else:
layer_outputs = layer_module(
hidden_states,
attention_mask,
layer_head_mask,
encoder_hidden_states,
encoder_attention_mask,
past_key_value,
output_attentions,
)
hidden_states = layer_outputs[0]
if use_cache:
next_decoder_cache += (layer_outputs[-1],)
if output_attentions:
all_self_attentions = all_self_attentions + (layer_outputs[1],)
if self.config.add_cross_attention:
all_cross_attentions = all_cross_attentions + (layer_outputs[2],)
if output_hidden_states:
all_hidden_states = all_hidden_states + (hidden_states,)
if not return_dict:
return tuple(
v
for v in [
hidden_states,
next_decoder_cache,
all_hidden_states,
all_self_attentions,
all_cross_attentions,
]
if v is not None
)
return BaseModelOutputWithPastAndCrossAttentions(
last_hidden_state=hidden_states,
past_key_values=next_decoder_cache,
hidden_states=all_hidden_states,
attentions=all_self_attentions,
cross_attentions=all_cross_attentions,
)
class MarkupLMPreTrainedModel(PreTrainedModel):
"""
An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
models.
"""
config_class = MarkupLMConfig
base_model_prefix = "markuplm"
# Copied from transformers.models.bert.modeling_bert.BertPreTrainedModel._init_weights with Bert->MarkupLM
def _init_weights(self, module):
"""Initialize the weights"""
if isinstance(module, nn.Linear):
# 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)
if module.bias is not None:
module.bias.data.zero_()
elif isinstance(module, nn.Embedding):
module.weight.data.normal_(mean=0.0, std=self.config.initializer_range)
if module.padding_idx is not None:
module.weight.data[module.padding_idx].zero_()
elif isinstance(module, nn.LayerNorm):
module.bias.data.zero_()
module.weight.data.fill_(1.0)
@classmethod
def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.PathLike]], *model_args, **kwargs):
return super(MarkupLMPreTrainedModel, cls).from_pretrained(
pretrained_model_name_or_path, *model_args, **kwargs
)
MARKUPLM_START_DOCSTRING = r"""
This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use
it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and
behavior.
Parameters:
config ([`MarkupLMConfig`]): 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.
"""
MARKUPLM_INPUTS_DOCSTRING = r"""
Args:
input_ids (`torch.LongTensor` of shape `({0})`):
Indices of input sequence tokens in the vocabulary.
Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
[`PreTrainedTokenizer.__call__`] for details.
[What are input IDs?](../glossary#input-ids)
xpath_tags_seq (`torch.LongTensor` of shape `({0}, config.max_depth)`, *optional*):
Tag IDs for each token in the input sequence, padded up to config.max_depth.
xpath_subs_seq (`torch.LongTensor` of shape `({0}, config.max_depth)`, *optional*):
Subscript IDs for each token in the input sequence, padded up to config.max_depth.
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 MASKED tokens.
[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 `(batch_size, sequence_length, 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.
output_attentions (`bool`, *optional*):
If set to `True`, the attentions tensors of all attention layers are returned. See `attentions` under
returned tensors for more detail.
output_hidden_states (`bool`, *optional*):
If set to `True`, the hidden states of all layers are returned. See `hidden_states` under returned tensors
for more detail.
return_dict (`bool`, *optional*):
If set to `True`, the model will return a [`~file_utils.ModelOutput`] instead of a plain tuple.
"""
@add_start_docstrings(
"The bare MarkupLM Model transformer outputting raw hidden-states without any specific head on top.",
MARKUPLM_START_DOCSTRING,
)
class MarkupLMModel(MarkupLMPreTrainedModel):
# Copied from transformers.models.bert.modeling_bert.BertModel.__init__ with Bert->MarkupLM
def __init__(self, config, add_pooling_layer=True):
super().__init__(config)
self.config = config
self.embeddings = MarkupLMEmbeddings(config)
self.encoder = MarkupLMEncoder(config)
self.pooler = MarkupLMPooler(config) if add_pooling_layer else None
# Initialize weights and apply final processing
self.post_init()
def get_input_embeddings(self):
return self.embeddings.word_embeddings
def set_input_embeddings(self, value):
self.embeddings.word_embeddings = value
def _prune_heads(self, heads_to_prune):
"""
Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base
class PreTrainedModel
"""
for layer, heads in heads_to_prune.items():
self.encoder.layer[layer].attention.prune_heads(heads)
@add_start_docstrings_to_model_forward(MARKUPLM_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@replace_return_docstrings(output_type=BaseModelOutputWithPoolingAndCrossAttentions, config_class=_CONFIG_FOR_DOC)
def forward(
self,
input_ids: Optional[torch.LongTensor] = None,
xpath_tags_seq: Optional[torch.LongTensor] = None,
xpath_subs_seq: Optional[torch.LongTensor] = None,
attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple, BaseModelOutputWithPoolingAndCrossAttentions]:
r"""
Returns:
Examples:
```python
>>> from transformers import AutoProcessor, MarkupLMModel
>>> processor = AutoProcessor.from_pretrained("microsoft/markuplm-base")
>>> model = MarkupLMModel.from_pretrained("microsoft/markuplm-base")
>>> html_string = "<html> <head> <title>Page Title</title> </head> </html>"
>>> encoding = processor(html_string, return_tensors="pt")
>>> outputs = model(**encoding)
>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 4, 768]
```"""
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 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:
self.warn_if_padding_and_no_attention_mask(input_ids, attention_mask)
input_shape = input_ids.size()
elif inputs_embeds is not None:
input_shape = inputs_embeds.size()[:-1]
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
if attention_mask is None:
attention_mask = torch.ones(input_shape, device=device)
if token_type_ids is None:
token_type_ids = torch.zeros(input_shape, dtype=torch.long, device=device)
extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)
extended_attention_mask = extended_attention_mask.to(dtype=self.dtype)
extended_attention_mask = (1.0 - extended_attention_mask) * -10000.0
if head_mask is not None:
if head_mask.dim() == 1:
head_mask = head_mask.unsqueeze(0).unsqueeze(0).unsqueeze(-1).unsqueeze(-1)
head_mask = head_mask.expand(self.config.num_hidden_layers, -1, -1, -1, -1)
elif head_mask.dim() == 2:
head_mask = head_mask.unsqueeze(1).unsqueeze(-1).unsqueeze(-1)
head_mask = head_mask.to(dtype=next(self.parameters()).dtype)
else:
head_mask = [None] * self.config.num_hidden_layers
embedding_output = self.embeddings(
input_ids=input_ids,
xpath_tags_seq=xpath_tags_seq,
xpath_subs_seq=xpath_subs_seq,
position_ids=position_ids,
token_type_ids=token_type_ids,
inputs_embeds=inputs_embeds,
)
encoder_outputs = self.encoder(
embedding_output,
extended_attention_mask,
head_mask=head_mask,
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,
hidden_states=encoder_outputs.hidden_states,
attentions=encoder_outputs.attentions,
cross_attentions=encoder_outputs.cross_attentions,
)
# Copied from transformers.models.bert.modeling_bert.BertModel.prepare_inputs_for_generation
def prepare_inputs_for_generation(
self, input_ids, past_key_values=None, attention_mask=None, use_cache=True, **model_kwargs
):
input_shape = input_ids.shape
# if model is used as a decoder in encoder-decoder model, the decoder attention mask is created on the fly
if attention_mask is None:
attention_mask = input_ids.new_ones(input_shape)
# cut decoder_input_ids if past_key_values is used
if past_key_values is not None:
past_length = past_key_values[0][0].shape[2]
# Some generation methods already pass only the last input ID
if input_ids.shape[1] > past_length:
remove_prefix_length = past_length
else:
# Default to old behavior: keep only final ID
remove_prefix_length = input_ids.shape[1] - 1
input_ids = input_ids[:, remove_prefix_length:]
return {
"input_ids": input_ids,
"attention_mask": attention_mask,
"past_key_values": past_key_values,
"use_cache": use_cache,
}
# Copied from transformers.models.bert.modeling_bert.BertModel._reorder_cache
def _reorder_cache(self, past_key_values, beam_idx):
reordered_past = ()
for layer_past in past_key_values:
reordered_past += (
tuple(past_state.index_select(0, beam_idx.to(past_state.device)) for past_state in layer_past),
)
return reordered_past
@add_start_docstrings(
"""
MarkupLM Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear
layers on top of the hidden-states output to compute `span start logits` and `span end logits`).
""",
MARKUPLM_START_DOCSTRING,
)
class MarkupLMForQuestionAnswering(MarkupLMPreTrainedModel):
# Copied from transformers.models.bert.modeling_bert.BertForQuestionAnswering.__init__ with bert->markuplm, Bert->MarkupLM
def __init__(self, config):
super().__init__(config)
self.num_labels = config.num_labels
self.markuplm = MarkupLMModel(config, add_pooling_layer=False)
self.qa_outputs = nn.Linear(config.hidden_size, config.num_labels)
# Initialize weights and apply final processing
self.post_init()
@add_start_docstrings_to_model_forward(MARKUPLM_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@replace_return_docstrings(output_type=QuestionAnsweringModelOutput, config_class=_CONFIG_FOR_DOC)
def forward(
self,
input_ids: Optional[torch.Tensor] = None,
xpath_tags_seq: Optional[torch.Tensor] = None,
xpath_subs_seq: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.Tensor] = None,
position_ids: 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,
) -> Union[Tuple[torch.Tensor], QuestionAnsweringModelOutput]:
r"""
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.
Returns:
Examples:
```python
>>> from transformers import AutoProcessor, MarkupLMForQuestionAnswering
>>> import torch
>>> processor = AutoProcessor.from_pretrained("microsoft/markuplm-base-finetuned-websrc")
>>> model = MarkupLMForQuestionAnswering.from_pretrained("microsoft/markuplm-base-finetuned-websrc")
>>> html_string = "<html> <head> <title>My name is Niels</title> </head> </html>"
>>> question = "What's his name?"
>>> encoding = processor(html_string, questions=question, return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**encoding)
>>> answer_start_index = outputs.start_logits.argmax()
>>> answer_end_index = outputs.end_logits.argmax()
>>> predict_answer_tokens = encoding.input_ids[0, answer_start_index : answer_end_index + 1]
>>> processor.decode(predict_answer_tokens).strip()
'Niels'
```"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
outputs = self.markuplm(
input_ids,
xpath_tags_seq=xpath_tags_seq,
xpath_subs_seq=xpath_subs_seq,
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,
)
sequence_output = outputs[0]
logits = self.qa_outputs(sequence_output)
start_logits, end_logits = logits.split(1, dim=-1)
start_logits = start_logits.squeeze(-1).contiguous()
end_logits = end_logits.squeeze(-1).contiguous()
total_loss = None
if start_positions is not None and end_positions is not None:
# If we are on multi-GPU, split add a dimension
if len(start_positions.size()) > 1:
start_positions = start_positions.squeeze(-1)
if len(end_positions.size()) > 1:
end_positions = end_positions.squeeze(-1)
# sometimes the start/end positions are outside our model inputs, we ignore these terms
ignored_index = start_logits.size(1)
start_positions.clamp_(0, ignored_index)
end_positions.clamp_(0, ignored_index)
loss_fct = CrossEntropyLoss(ignore_index=ignored_index)
start_loss = loss_fct(start_logits, start_positions)
end_loss = loss_fct(end_logits, end_positions)
total_loss = (start_loss + end_loss) / 2
if not return_dict:
output = (start_logits, end_logits) + outputs[2:]
return ((total_loss,) + output) if total_loss is not None else output
return QuestionAnsweringModelOutput(
loss=total_loss,
start_logits=start_logits,
end_logits=end_logits,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)
@add_start_docstrings("""MarkupLM Model with a `token_classification` head on top.""", MARKUPLM_START_DOCSTRING)
class MarkupLMForTokenClassification(MarkupLMPreTrainedModel):
# Copied from transformers.models.bert.modeling_bert.BertForTokenClassification.__init__ with bert->markuplm, Bert->MarkupLM
def __init__(self, config):
super().__init__(config)
self.num_labels = config.num_labels
self.markuplm = MarkupLMModel(config, add_pooling_layer=False)
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, config.num_labels)
# Initialize weights and apply final processing
self.post_init()
@add_start_docstrings_to_model_forward(MARKUPLM_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@replace_return_docstrings(output_type=MaskedLMOutput, config_class=_CONFIG_FOR_DOC)
def forward(
self,
input_ids: Optional[torch.Tensor] = None,
xpath_tags_seq: Optional[torch.Tensor] = None,
xpath_subs_seq: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.Tensor] = None,
position_ids: Optional[torch.Tensor] = None,
head_mask: Optional[torch.Tensor] = None,
inputs_embeds: Optional[torch.Tensor] = None,
labels: Optional[torch.Tensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple[torch.Tensor], MaskedLMOutput]:
r"""
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
Returns:
Examples:
```python
>>> from transformers import AutoProcessor, AutoModelForTokenClassification
>>> import torch
>>> processor = AutoProcessor.from_pretrained("microsoft/markuplm-base")
>>> processor.parse_html = False
>>> model = AutoModelForTokenClassification.from_pretrained("microsoft/markuplm-base", num_labels=7)
>>> nodes = ["hello", "world"]
>>> xpaths = ["/html/body/div/li[1]/div/span", "/html/body/div/li[1]/div/span"]
>>> node_labels = [1, 2]
>>> encoding = processor(nodes=nodes, xpaths=xpaths, node_labels=node_labels, return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**encoding)
>>> loss = outputs.loss
>>> logits = outputs.logits
```"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
outputs = self.markuplm(
input_ids,
xpath_tags_seq=xpath_tags_seq,
xpath_subs_seq=xpath_subs_seq,
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,
)
sequence_output = outputs[0]
prediction_scores = self.classifier(sequence_output) # (batch_size, seq_length, node_type_size)
loss = None
if labels is not None:
loss_fct = CrossEntropyLoss()
loss = loss_fct(
prediction_scores.view(-1, self.config.num_labels),
labels.view(-1),
)
if not return_dict:
output = (prediction_scores,) + outputs[2:]
return ((loss,) + output) if loss is not None else output
return TokenClassifierOutput(
loss=loss,
logits=prediction_scores,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)
@add_start_docstrings(
"""
MarkupLM Model transformer with a sequence classification/regression head on top (a linear layer on top of the
pooled output) e.g. for GLUE tasks.
""",
MARKUPLM_START_DOCSTRING,
)
class MarkupLMForSequenceClassification(MarkupLMPreTrainedModel):
# Copied from transformers.models.bert.modeling_bert.BertForSequenceClassification.__init__ with bert->markuplm, Bert->MarkupLM
def __init__(self, config):
super().__init__(config)
self.num_labels = config.num_labels
self.config = config
self.markuplm = MarkupLMModel(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, config.num_labels)
# Initialize weights and apply final processing
self.post_init()
@add_start_docstrings_to_model_forward(MARKUPLM_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@replace_return_docstrings(output_type=SequenceClassifierOutput, config_class=_CONFIG_FOR_DOC)
def forward(
self,
input_ids: Optional[torch.Tensor] = None,
xpath_tags_seq: Optional[torch.Tensor] = None,
xpath_subs_seq: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.Tensor] = None,
position_ids: Optional[torch.Tensor] = None,
head_mask: Optional[torch.Tensor] = None,
inputs_embeds: Optional[torch.Tensor] = None,
labels: Optional[torch.Tensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple[torch.Tensor], SequenceClassifierOutput]:
r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
`config.num_labels > 1` a classification loss is computed (Cross-Entropy).
Returns:
Examples:
```python
>>> from transformers import AutoProcessor, AutoModelForSequenceClassification
>>> import torch
>>> processor = AutoProcessor.from_pretrained("microsoft/markuplm-base")
>>> model = AutoModelForSequenceClassification.from_pretrained("microsoft/markuplm-base", num_labels=7)
>>> html_string = "<html> <head> <title>Page Title</title> </head> </html>"
>>> encoding = processor(html_string, return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**encoding)
>>> loss = outputs.loss
>>> logits = outputs.logits
```"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
outputs = self.markuplm(
input_ids,
xpath_tags_seq=xpath_tags_seq,
xpath_subs_seq=xpath_subs_seq,
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,
)
pooled_output = outputs[1]
pooled_output = self.dropout(pooled_output)
logits = self.classifier(pooled_output)
loss = None
if labels is not None:
if self.config.problem_type is None:
if self.num_labels == 1:
self.config.problem_type = "regression"
elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
self.config.problem_type = "single_label_classification"
else:
self.config.problem_type = "multi_label_classification"
if self.config.problem_type == "regression":
loss_fct = MSELoss()
if self.num_labels == 1:
loss = loss_fct(logits.squeeze(), labels.squeeze())
else:
loss = loss_fct(logits, labels)
elif self.config.problem_type == "single_label_classification":
loss_fct = CrossEntropyLoss()
loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
elif self.config.problem_type == "multi_label_classification":
loss_fct = BCEWithLogitsLoss()
loss = loss_fct(logits, labels)
if not return_dict:
output = (logits,) + outputs[2:]
return ((loss,) + output) if loss is not None else output
return SequenceClassifierOutput(
loss=loss,
logits=logits,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)