LayoutLM¶
Overview¶
The LayoutLM model was proposed in the paper LayoutLM: Pre-training of Text and Layout for Document Image Understanding by Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, and Ming Zhou. It’s a simple but effective pretraining method of text and layout for document image understanding and information extraction tasks, such as form understanding and receipt understanding.
The abstract from the paper is the following:
Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pretraining models for NLP applications, they almost exclusively focus on text-level manipulation, while neglecting layout and style information that is vital for document image understanding. In this paper, we propose the textbf{LayoutLM} to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned documents. Furthermore, we also leverage image features to incorporate words’ visual information into LayoutLM. To the best of our knowledge, this is the first time that text and layout are jointly learned in a single framework for document-level pretraining. It achieves new state-of-the-art results in several downstream tasks, including form understanding (from 70.72 to 79.27), receipt understanding (from 94.02 to 95.24) and document image classification (from 93.07 to 94.42).
Tips:
LayoutLM has an extra input called
bbox
, which is the bounding boxes of the input tokens.The
bbox
requires the data that on 0-1000 scale, which means you should normalize the bounding box before passing them into model.
The original code can be found here.
LayoutLMConfig¶
-
class
transformers.
LayoutLMConfig
(vocab_size=30522, 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, layer_norm_eps=1e-12, pad_token_id=0, gradient_checkpointing=False, max_2d_position_embeddings=1024, **kwargs)[source]¶ This is the configuration class to store the configuration of a
LayoutLMModel
. It is used to instantiate a LayoutLM model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the LayoutLM layoutlm-base-uncased architecture.Configuration objects inherit from
BertConfig
and can be used to control the model outputs. Read the documentation fromBertConfig
for more information.- Parameters
vocab_size (
int
, optional, defaults to 30522) – Vocabulary size of the LayoutLM model. Defines the different tokens that can be represented by the inputs_ids passed to the forward method ofLayoutLMModel
.hidden_size (
int
, optional, defaults to 768) – Dimensionality of the encoder layers and the pooler layer.num_hidden_layers (
int
, optional, defaults to 12) – Number of hidden layers in the Transformer encoder.num_attention_heads (
int
, optional, defaults to 12) – Number of attention heads for each attention layer in the Transformer encoder.intermediate_size (
int
, optional, defaults to 3072) – Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.hidden_act (
str
orfunction
, optional, defaults to"gelu"
) – The non-linear activation function (function or string) in the encoder and pooler. If string,"gelu"
,"relu"
,"silu"
and"gelu_new"
are supported.hidden_dropout_prob (
float
, optional, defaults to 0.1) – The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.attention_probs_dropout_prob (
float
, optional, defaults to 0.1) – The dropout ratio for the attention probabilities.max_position_embeddings (
int
, optional, defaults to 512) – 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 (
int
, optional, defaults to 2) – The vocabulary size of thetoken_type_ids
passed intoLayoutLMModel
.initializer_range (
float
, optional, defaults to 0.02) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices.layer_norm_eps (
float
, optional, defaults to 1e-12) – The epsilon used by the layer normalization layers.gradient_checkpointing (
bool
, optional, defaults toFalse
) – If True, use gradient checkpointing to save memory at the expense of slower backward pass.max_2d_position_embeddings (
int
, optional, defaults to 1024) – The maximum value that the 2D position embedding might ever used. Typically set this to something large just in case (e.g., 1024).
Examples:
>>> from transformers import LayoutLMModel, LayoutLMConfig >>> # Initializing a LayoutLM configuration >>> configuration = LayoutLMConfig() >>> # Initializing a model from the configuration >>> model = LayoutLMModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config
LayoutLMTokenizer¶
-
class
transformers.
LayoutLMTokenizer
(vocab_file, do_lower_case=True, do_basic_tokenize=True, never_split=None, unk_token='[UNK]', sep_token='[SEP]', pad_token='[PAD]', cls_token='[CLS]', mask_token='[MASK]', tokenize_chinese_chars=True, strip_accents=None, **kwargs)[source]¶ Constructs a LayoutLM tokenizer.
BertTokenizer
and runs end-to-end tokenization: punctuation splitting + wordpiece.Refer to superclass
BertTokenizer
for usage examples and documentation concerning parameters.
LayoutLMModel¶
-
class
transformers.
LayoutLMModel
(config)[source]¶ The bare LayoutLM Model transformer outputting raw hidden-states without any specific head on top. The LayoutLM model was proposed in LayoutLM: Pre-training of Text and Layout for Document Image Understanding by….
This model is a PyTorch 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 (
LayoutLMConfig
) – 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 thefrom_pretrained()
method to load the model weights.
-
config_class
¶ alias of
transformers.models.layoutlm.configuration_layoutlm.LayoutLMConfig
-
forward
(input_ids=None, bbox=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, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶ The
LayoutLMModel
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.LayoutLMTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.bbox (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Bounding Boxes of each input sequence tokens. Selected in the range
[0, config.max_2d_position_embeddings - 1]
.attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), 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.token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), 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 tokenposition_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) –
Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.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. Seeattentions
under returned tensors for more detail.output_hidden_states (bool, optional) – If set to
True
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (bool, optional) – If set to
True
, the model will return aModelOutput
instead of a plain tuple.input_ids – Indices of input sequence tokens in the vocabulary.
attention_mask – 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.
token_type_ids – 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
position_ids – Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].
head_mask – 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 – 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 – If set to True, the attentions tensors of all attention layers are returned.
output_hidden_states – If set to True, the hidden states of all layers are returned.
return_dict – If set to True, the model will return a ModelOutput instead of a plain tuple.
- Returns
A
BaseModelOutputWithPoolingAndCrossAttentions
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (LayoutLMConfig
) and inputs.last_hidden_state (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
) – Sequence of hidden-states at the output of the last layer of the model.pooler_output (
torch.FloatTensor
of shape(batch_size, hidden_size)
) – Last layer hidden-state of the first token of the sequence (classification token) further processed by a Linear layer and a Tanh activation function. The Linear layer weights are trained from the next sentence prediction (classification) objective during pretraining.hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + 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 initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.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.
cross_attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
andconfig.add_cross_attention=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
- Return type
BaseModelOutputWithPoolingAndCrossAttentions
ortuple(torch.FloatTensor)
Example:
>>> from transformers import LayoutLMTokenizer, LayoutLMModel >>> import torch >>> tokenizer = LayoutLMTokenizer.from_pretrained('layoutlm-base-uncased') >>> model = LayoutLMModel.from_pretrained('layoutlm-base-uncased') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> outputs = model(**inputs) >>> last_hidden_states = outputs.last_hidden_state
LayoutLMForMaskedLM¶
-
class
transformers.
LayoutLMForMaskedLM
(config)[source]¶ LayoutLM Model with a language modeling head on top. The LayoutLM model was proposed in LayoutLM: Pre-training of Text and Layout for Document Image Understanding by….
This model is a PyTorch 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 (
LayoutLMConfig
) – 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 thefrom_pretrained()
method to load the model weights.
-
config_class
¶ alias of
transformers.models.layoutlm.configuration_layoutlm.LayoutLMConfig
-
forward
(input_ids=None, bbox=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, encoder_hidden_states=None, encoder_attention_mask=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶ The
LayoutLMForMaskedLM
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.LayoutLMTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.bbox (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Bounding Boxes of each input sequence tokens. Selected in the range
[0, config.max_2d_position_embeddings - 1]
.attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, 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.token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, 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 tokenposition_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.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 passinginput_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 toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.
- Returns
A
MaskedLMOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (LayoutLMConfig
) and inputs.loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) – Masked language modeling (MLM) loss.logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) – Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + 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 initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.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.
- Return type
MaskedLMOutput
ortuple(torch.FloatTensor)
Example:
>>> from transformers import LayoutLMTokenizer, LayoutLMForMaskedLM >>> import torch >>> tokenizer = LayoutLMTokenizer.from_pretrained('layoutlm-base-uncased') >>> model = LayoutLMForMaskedLM.from_pretrained('layoutlm-base-uncased') >>> inputs = tokenizer("The capital of France is [MASK].", return_tensors="pt") >>> labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"] >>> outputs = model(**inputs, labels=labels) >>> loss = outputs.loss >>> logits = outputs.logits
LayoutLMForTokenClassification¶
-
class
transformers.
LayoutLMForTokenClassification
(config)[source]¶ LayoutLM Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks.
The LayoutLM model was proposed in LayoutLM: Pre-training of Text and Layout for Document Image Understanding by….
This model is a PyTorch 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 (
LayoutLMConfig
) – 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 thefrom_pretrained()
method to load the model weights.
-
config_class
¶ alias of
transformers.models.layoutlm.configuration_layoutlm.LayoutLMConfig
-
forward
(input_ids=None, bbox=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)[source]¶ The
LayoutLMForTokenClassification
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.LayoutLMTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.bbox (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Bounding Boxes of each input sequence tokens. Selected in the range
[0, config.max_2d_position_embeddings - 1]
.attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, 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.token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, 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 tokenposition_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.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 passinginput_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 toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.
- Returns
A
TokenClassifierOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (LayoutLMConfig
) and inputs.loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) – Classification loss.logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.num_labels)
) – Classification scores (before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + 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 initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.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.
- Return type
TokenClassifierOutput
ortuple(torch.FloatTensor)
Example:
>>> from transformers import LayoutLMTokenizer, LayoutLMForTokenClassification >>> import torch >>> tokenizer = LayoutLMTokenizer.from_pretrained('layoutlm-base-uncased') >>> model = LayoutLMForTokenClassification.from_pretrained('layoutlm-base-uncased') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> labels = torch.tensor([1] * inputs["input_ids"].size(1)).unsqueeze(0) # Batch size 1 >>> outputs = model(**inputs, labels=labels) >>> loss = outputs.loss >>> logits = outputs.logits