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. It obtains state-of-the-art results on several downstream tasks:

• form understanding: the FUNSD dataset (a collection of 199 annotated forms comprising more than 30,000 words).

• receipt understanding: the SROIE dataset (a collection of 626 receipts for training and 347 receipts for testing).

• document image classification: the RVL-CDIP dataset (a collection of 400,000 images belonging to one of 16 classes).

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 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:

• In addition to input_ids, forward() also expects the input bbox, which are the bounding boxes (i.e. 2D-positions) of the input tokens. These can be obtained using an external OCR engine such as Google’s Tesseract (there’s a Python wrapper available). Each bounding box should be in (x0, y0, x1, y1) format, where (x0, y0) corresponds to the position of the upper left corner in the bounding box, and (x1, y1) represents the position of the lower right corner. Note that one first needs to normalize the bounding boxes to be on a 0-1000 scale. To normalize, you can use the following function:

def normalize_bbox(bbox, width, height):
     return [
         int(1000 * (bbox[0] / width)),
         int(1000 * (bbox[1] / height)),
         int(1000 * (bbox[2] / width)),
         int(1000 * (bbox[3] / height)),
     ]

Here, width and height correspond to the width and height of the original document in which the token occurs. Those can be obtained using the Python Image Library (PIL) library for example, as follows:

from PIL import Image

image = Image.open("name_of_your_document - can be a png file, pdf, etc.")

width, height = image.size

• For a demo which shows how to fine-tune LayoutLMForTokenClassification on the FUNSD dataset (a collection of annotated forms), see this notebook. It includes an inference part, which shows how to use Google’s Tesseract on a new document.

This model was contributed by liminghao1630. 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)

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 from BertConfig 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 of LayoutLMModel.

• 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 or function, 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 the token_type_ids passed into LayoutLMModel.

• 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 to False) – 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)

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.

LayoutLMTokenizerFast

class transformers.LayoutLMTokenizerFast(vocab_file, tokenizer_file=None, do_lower_case=True, unk_token='[UNK]', sep_token='[SEP]', pad_token='[PAD]', cls_token='[CLS]', mask_token='[MASK]', tokenize_chinese_chars=True, strip_accents=None, **kwargs)

Constructs a “Fast” LayoutLMTokenizer.

LayoutLMTokenizerFast is identical to BertTokenizerFast and runs end-to-end tokenization: punctuation splitting + wordpiece.

Refer to superclass BertTokenizerFast for usage examples and documentation concerning parameters.

slow_tokenizer_class

alias of transformers.models.layoutlm.tokenization_layoutlm.LayoutLMTokenizer

LayoutLMModel

class transformers.LayoutLMModel(config)

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 Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei and Ming Zhou.

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 the from_pretrained() method to load the model weights.

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)

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. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

  What are input IDs?

• bbox (torch.LongTensor of shape (batch_size, sequence_length, 4), optional) – Bounding boxes of each input sequence tokens. Selected in the range [0, config.max_2d_position_embeddings-1]. Each bounding box should be a normalized version in (x0, y0, x1, y1) format, where (x0, y0) corresponds to the position of the upper left corner in the bounding box, and (x1, y1) represents the position of the lower right corner. See Overview for normalization.

• 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.

  What are attention masks?

• 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 token

  What are token type IDs?

• position_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].

  What are 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 ModelOutput instead of a plain tuple.

Returns

A BaseModelOutputWithPoolingAndCrossAttentions or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) 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 when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of torch.FloatTensor (one for the output of the embeddings + 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 when output_attentions=True is passed or when config.output_attentions=True) – Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

• cross_attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True and config.add_cross_attention=True is passed or when config.output_attentions=True) – Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and optionally if config.is_encoder_decoder=True 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

  Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if config.is_encoder_decoder=True in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

Examples:

>>> from transformers import LayoutLMTokenizer, LayoutLMModel
>>> import torch

>>> tokenizer = LayoutLMTokenizer.from_pretrained('microsoft/layoutlm-base-uncased')
>>> model = LayoutLMModel.from_pretrained('microsoft/layoutlm-base-uncased')

>>> words = ["Hello", "world"]
>>> normalized_word_boxes = [637, 773, 693, 782], [698, 773, 733, 782]

>>> token_boxes = []
>>> for word, box in zip(words, normalized_word_boxes):
...     word_tokens = tokenizer.tokenize(word)
...     token_boxes.extend([box] * len(word_tokens))
>>> # add bounding boxes of cls + sep tokens
>>> token_boxes = [[0, 0, 0, 0]] + token_boxes + [[1000, 1000, 1000, 1000]]

>>> encoding = tokenizer(' '.join(words), return_tensors="pt")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = torch.tensor([token_boxes])

>>> outputs = model(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask, token_type_ids=token_type_ids)

>>> last_hidden_states = outputs.last_hidden_state

Return type

BaseModelOutputWithPoolingAndCrossAttentions or tuple(torch.FloatTensor)

get_input_embeddings()

Returns the model’s input embeddings.

Returns

A torch module mapping vocabulary to hidden states.

Return type

nn.Module

set_input_embeddings(value)

Set model’s input embeddings.

Parameters

value (nn.Module) – A module mapping vocabulary to hidden states.

LayoutLMForMaskedLM

class transformers.LayoutLMForMaskedLM(config)

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 Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei and Ming Zhou.

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 the from_pretrained() method to load the model weights.

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)

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. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

  What are input IDs?

• bbox (torch.LongTensor of shape (batch_size, sequence_length, 4), optional) – Bounding boxes of each input sequence tokens. Selected in the range [0, config.max_2d_position_embeddings-1]. Each bounding box should be a normalized version in (x0, y0, x1, y1) format, where (x0, y0) corresponds to the position of the upper left corner in the bounding box, and (x1, y1) represents the position of the lower right corner. See Overview for normalization.

• 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.

  What are attention masks?

• 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 token

  What are token type IDs?

• position_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].

  What are 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 ModelOutput instead of a plain tuple.

• labels (torch.LongTensor of shape (batch_size, sequence_length), optional) – Labels for computing the masked language modeling loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

Returns

A MaskedLMOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (LayoutLMConfig) and inputs.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels 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 when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of torch.FloatTensor (one for the output of the embeddings + 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 when output_attentions=True is passed or when config.output_attentions=True) – Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Examples:

>>> from transformers import LayoutLMTokenizer, LayoutLMForMaskedLM
>>> import torch

>>> tokenizer = LayoutLMTokenizer.from_pretrained('microsoft/layoutlm-base-uncased')
>>> model = LayoutLMForMaskedLM.from_pretrained('microsoft/layoutlm-base-uncased')

>>> words = ["Hello", "[MASK]"]
>>> normalized_word_boxes = [637, 773, 693, 782], [698, 773, 733, 782]

>>> token_boxes = []
>>> for word, box in zip(words, normalized_word_boxes):
...     word_tokens = tokenizer.tokenize(word)
...     token_boxes.extend([box] * len(word_tokens))
>>> # add bounding boxes of cls + sep tokens
>>> token_boxes = [[0, 0, 0, 0]] + token_boxes + [[1000, 1000, 1000, 1000]]

>>> encoding = tokenizer(' '.join(words), return_tensors="pt")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = torch.tensor([token_boxes])

>>> labels = tokenizer("Hello world", return_tensors="pt")["input_ids"]

>>> outputs = model(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask, token_type_ids=token_type_ids,
...                 labels=labels)

>>> loss = outputs.loss

Return type

MaskedLMOutput or tuple(torch.FloatTensor)

get_input_embeddings()

Returns the model’s input embeddings.

Returns

A torch module mapping vocabulary to hidden states.

Return type

nn.Module

get_output_embeddings()

Returns the model’s output embeddings.

Returns

A torch module mapping hidden states to vocabulary.

Return type

nn.Module

LayoutLMForSequenceClassification

class transformers.LayoutLMForSequenceClassification(config)

LayoutLM Model with a sequence classification head on top (a linear layer on top of the pooled output) e.g. for document image classification tasks such as the RVL-CDIP dataset.

The LayoutLM model was proposed in 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.

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 the from_pretrained() method to load the model weights.

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)

The LayoutLMForSequenceClassification 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. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

  What are input IDs?

• bbox (torch.LongTensor of shape (batch_size, sequence_length, 4), optional) – Bounding boxes of each input sequence tokens. Selected in the range [0, config.max_2d_position_embeddings-1]. Each bounding box should be a normalized version in (x0, y0, x1, y1) format, where (x0, y0) corresponds to the position of the upper left corner in the bounding box, and (x1, y1) represents the position of the lower right corner. See Overview for normalization.

• 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.

  What are attention masks?

• 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 token

  What are token type IDs?

• position_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].

  What are 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 ModelOutput instead of a plain tuple.

• 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

A SequenceClassifierOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (LayoutLMConfig) and inputs.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) – Classification (or regression if config.num_labels==1) loss.

• logits (torch.FloatTensor of shape (batch_size, config.num_labels)) – Classification (or regression if config.num_labels==1) scores (before SoftMax).

• hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of torch.FloatTensor (one for the output of the embeddings + 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 when output_attentions=True is passed or when config.output_attentions=True) – Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Examples:

>>> from transformers import LayoutLMTokenizer, LayoutLMForSequenceClassification
>>> import torch

>>> tokenizer = LayoutLMTokenizer.from_pretrained('microsoft/layoutlm-base-uncased')
>>> model = LayoutLMForSequenceClassification.from_pretrained('microsoft/layoutlm-base-uncased')

>>> words = ["Hello", "world"]
>>> normalized_word_boxes = [637, 773, 693, 782], [698, 773, 733, 782]

>>> token_boxes = []
>>> for word, box in zip(words, normalized_word_boxes):
...     word_tokens = tokenizer.tokenize(word)
...     token_boxes.extend([box] * len(word_tokens))
>>> # add bounding boxes of cls + sep tokens
>>> token_boxes = [[0, 0, 0, 0]] + token_boxes + [[1000, 1000, 1000, 1000]]

>>> encoding = tokenizer(' '.join(words), return_tensors="pt")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = torch.tensor([token_boxes])
>>> sequence_label = torch.tensor([1])

>>> outputs = model(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask, token_type_ids=token_type_ids,
...                 labels=sequence_label)

>>> loss = outputs.loss
>>> logits = outputs.logits

Return type

SequenceClassifierOutput or tuple(torch.FloatTensor)

get_input_embeddings()

Returns the model’s input embeddings.

Returns

A torch module mapping vocabulary to hidden states.

Return type

nn.Module

LayoutLMForTokenClassification

class transformers.LayoutLMForTokenClassification(config)

LayoutLM Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for sequence labeling (information extraction) tasks such as the FUNSD dataset and the SROIE dataset.

The LayoutLM model was proposed in 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.

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 the from_pretrained() method to load the model weights.

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)

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. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

  What are input IDs?

• bbox (torch.LongTensor of shape (batch_size, sequence_length, 4), optional) – Bounding boxes of each input sequence tokens. Selected in the range [0, config.max_2d_position_embeddings-1]. Each bounding box should be a normalized version in (x0, y0, x1, y1) format, where (x0, y0) corresponds to the position of the upper left corner in the bounding box, and (x1, y1) represents the position of the lower right corner. See Overview for normalization.

• 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.

  What are attention masks?

• 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 token

  What are token type IDs?

• position_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].

  What are 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 ModelOutput instead of a plain tuple.

• 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

A TokenClassifierOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (LayoutLMConfig) and inputs.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels 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 when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of torch.FloatTensor (one for the output of the embeddings + 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 when output_attentions=True is passed or when config.output_attentions=True) – Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Examples:

>>> from transformers import LayoutLMTokenizer, LayoutLMForTokenClassification
>>> import torch

>>> tokenizer = LayoutLMTokenizer.from_pretrained('microsoft/layoutlm-base-uncased')
>>> model = LayoutLMForTokenClassification.from_pretrained('microsoft/layoutlm-base-uncased')

>>> words = ["Hello", "world"]
>>> normalized_word_boxes = [637, 773, 693, 782], [698, 773, 733, 782]

>>> token_boxes = []
>>> for word, box in zip(words, normalized_word_boxes):
...     word_tokens = tokenizer.tokenize(word)
...     token_boxes.extend([box] * len(word_tokens))
>>> # add bounding boxes of cls + sep tokens
>>> token_boxes = [[0, 0, 0, 0]] + token_boxes + [[1000, 1000, 1000, 1000]]

>>> encoding = tokenizer(' '.join(words), return_tensors="pt")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = torch.tensor([token_boxes])
>>> token_labels = torch.tensor([1,1,0,0]).unsqueeze(0) # batch size of 1

>>> outputs = model(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask, token_type_ids=token_type_ids,
...                 labels=token_labels)

>>> loss = outputs.loss
>>> logits = outputs.logits

Return type

TokenClassifierOutput or tuple(torch.FloatTensor)

get_input_embeddings()

Returns the model’s input embeddings.

Returns

A torch module mapping vocabulary to hidden states.

Return type

nn.Module

TFLayoutLMModel

class transformers.TFLayoutLMModel(*args, **kwargs)

The bare LayoutLM Model transformer outputting raw hidden-states without any specific head on top.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

• having all inputs as keyword arguments (like PyTorch models), or

• having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

• a single Tensor with input_ids only and nothing else: model(inputs_ids)

• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])

• a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

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 the from_pretrained() method to load the model weights.

call(input_ids: Optional[Union[List[tensorflow.python.framework.ops.Tensor], List[numpy.ndarray], Dict[str, tensorflow.python.framework.ops.Tensor], Dict[str, numpy.ndarray], numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, bbox: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, attention_mask: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, token_type_ids: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, position_ids: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, head_mask: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, inputs_embeds: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, training: Optional[bool] = False, **kwargs) → Union[transformers.modeling_tf_outputs.TFBaseModelOutputWithPooling, Tuple[tensorflow.python.framework.ops.Tensor]]

The TFLayoutLMModel 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 (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) –

  Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using LayoutLMTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

  What are input IDs?

• bbox (Numpy array or tf.Tensor of shape (batch_size, sequence_length, 4), optional) – Bounding Boxes of each input sequence tokens. Selected in the range [0, config.max_2d_position_embeddings- 1].

• attention_mask (Numpy array or tf.Tensor 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 tokens that are masked.

  What are attention masks?

• token_type_ids (Numpy array or tf.Tensor 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 token.

  What are token type IDs?

• position_ids (Numpy array or tf.Tensor 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].

  What are position IDs?

• head_mask (Numpy array or tf.Tensor 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 (tf.Tensor 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) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

• output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

• return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

• training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

Returns

A TFBaseModelOutputWithPooling or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (LayoutLMConfig) and inputs.

• last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size)) – Sequence of hidden-states at the output of the last layer of the model.

• pooler_output (tf.Tensor 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.

  This output is usually not a good summary of the semantic content of the input, you’re often better with averaging or pooling the sequence of hidden-states for the whole input sequence.

• hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (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(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Examples:

>>> from transformers import LayoutLMTokenizer, TFLayoutLMModel
>>> import tensorflow as tf

>>> tokenizer = LayoutLMTokenizer.from_pretrained('microsoft/layoutlm-base-uncased')
>>> model = TFLayoutLMModel.from_pretrained('microsoft/layoutlm-base-uncased')

>>> words = ["Hello", "world"]
>>> normalized_word_boxes = [637, 773, 693, 782], [698, 773, 733, 782]

>>> token_boxes = []
>>> for word, box in zip(words, normalized_word_boxes):
...     word_tokens = tokenizer.tokenize(word)
...     token_boxes.extend([box] * len(word_tokens))
>>> # add bounding boxes of cls + sep tokens
>>> token_boxes = [[0, 0, 0, 0]] + token_boxes + [[1000, 1000, 1000, 1000]]

>>> encoding = tokenizer(' '.join(words), return_tensors="tf")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = tf.convert_to_tensor([token_boxes])

>>> outputs = model(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask, token_type_ids=token_type_ids)

>>> last_hidden_states = outputs.last_hidden_state

Return type

TFBaseModelOutputWithPooling or tuple(tf.Tensor)

serving_output(output: transformers.modeling_tf_outputs.TFBaseModelOutputWithPooling) → transformers.modeling_tf_outputs.TFBaseModelOutputWithPooling

Prepare the output of the saved model. Each model must implement this function.

Parameters

output (TFBaseModelOutput) – The output returned by the model.

TFLayoutLMForMaskedLM

class transformers.TFLayoutLMForMaskedLM(*args, **kwargs)

LayoutLM Model with a language modeling head on top.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

• having all inputs as keyword arguments (like PyTorch models), or

• having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

• a single Tensor with input_ids only and nothing else: model(inputs_ids)

• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])

• a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

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 the from_pretrained() method to load the model weights.

call(input_ids: Optional[Union[List[tensorflow.python.framework.ops.Tensor], List[numpy.ndarray], Dict[str, tensorflow.python.framework.ops.Tensor], Dict[str, numpy.ndarray], numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, bbox: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, attention_mask: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, token_type_ids: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, position_ids: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, head_mask: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, inputs_embeds: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, labels: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, training: Optional[bool] = False, **kwargs) → Union[transformers.modeling_tf_outputs.TFMaskedLMOutput, Tuple[tensorflow.python.framework.ops.Tensor]]

The TFLayoutLMForMaskedLM 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 (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) –

  Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using LayoutLMTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

  What are input IDs?

• bbox (Numpy array or tf.Tensor of shape (batch_size, sequence_length, 4), optional) – Bounding Boxes of each input sequence tokens. Selected in the range [0, config.max_2d_position_embeddings- 1].

• attention_mask (Numpy array or tf.Tensor 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 tokens that are masked.

  What are attention masks?

• token_type_ids (Numpy array or tf.Tensor 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 token.

  What are token type IDs?

• position_ids (Numpy array or tf.Tensor 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].

  What are position IDs?

• head_mask (Numpy array or tf.Tensor 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 (tf.Tensor 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) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

• output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

• return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

• training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

• labels (tf.Tensor or np.ndarray of shape (batch_size, sequence_length), optional) – Labels for computing the masked language modeling loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

Returns

A TFMaskedLMOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (LayoutLMConfig) and inputs.

• loss (tf.Tensor of shape (n,), optional, where n is the number of non-masked labels, returned when labels is provided) – Masked language modeling (MLM) loss.

• logits (tf.Tensor 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(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (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(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Examples:

>>> from transformers import LayoutLMTokenizer, TFLayoutLMForMaskedLM
>>> import tensorflow as tf

>>> tokenizer = LayoutLMTokenizer.from_pretrained('microsoft/layoutlm-base-uncased')
>>> model = TFLayoutLMForMaskedLM.from_pretrained('microsoft/layoutlm-base-uncased')

>>> words = ["Hello", "[MASK]"]
>>> normalized_word_boxes = [637, 773, 693, 782], [698, 773, 733, 782]

>>> token_boxes = []
>>> for word, box in zip(words, normalized_word_boxes):
...     word_tokens = tokenizer.tokenize(word)
...     token_boxes.extend([box] * len(word_tokens))
>>> # add bounding boxes of cls + sep tokens
>>> token_boxes = [[0, 0, 0, 0]] + token_boxes + [[1000, 1000, 1000, 1000]]

>>> encoding = tokenizer(' '.join(words), return_tensors="tf")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = tf.convert_to_tensor([token_boxes])

>>> labels = tokenizer("Hello world", return_tensors="tf")["input_ids"]

>>> outputs = model(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask, token_type_ids=token_type_ids,
...                 labels=labels)

>>> loss = outputs.loss

Return type

TFMaskedLMOutput or tuple(tf.Tensor)

get_lm_head() → tensorflow.python.keras.engine.base_layer.Layer

The LM Head layer. This method must be overwritten by all the models that have a lm head.

Returns

The LM head layer if the model has one, None if not.

Return type

tf.keras.layers.Layer

get_prefix_bias_name() → str

Get the concatenated _prefix name of the bias from the model name to the parent layer

Returns

The _prefix name of the bias.

Return type

str

serving_output(output: transformers.modeling_tf_outputs.TFMaskedLMOutput) → transformers.modeling_tf_outputs.TFMaskedLMOutput

Prepare the output of the saved model. Each model must implement this function.

Parameters

output (TFBaseModelOutput) – The output returned by the model.

TFLayoutLMForSequenceClassification

class transformers.TFLayoutLMForSequenceClassification(*args, **kwargs)

LayoutLM Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

• having all inputs as keyword arguments (like PyTorch models), or

• having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

• a single Tensor with input_ids only and nothing else: model(inputs_ids)

• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])

• a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

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 the from_pretrained() method to load the model weights.

call(input_ids: Optional[Union[List[tensorflow.python.framework.ops.Tensor], List[numpy.ndarray], Dict[str, tensorflow.python.framework.ops.Tensor], Dict[str, numpy.ndarray], numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, bbox: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, attention_mask: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, token_type_ids: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, position_ids: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, head_mask: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, inputs_embeds: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, labels: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, training: Optional[bool] = False, **kwargs) → Union[transformers.modeling_tf_outputs.TFSequenceClassifierOutput, Tuple[tensorflow.python.framework.ops.Tensor]]

The TFLayoutLMForSequenceClassification 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 (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) –

  Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using LayoutLMTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

  What are input IDs?

• bbox (Numpy array or tf.Tensor of shape (batch_size, sequence_length, 4), optional) – Bounding Boxes of each input sequence tokens. Selected in the range [0, config.max_2d_position_embeddings- 1].

• attention_mask (Numpy array or tf.Tensor 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 tokens that are masked.

  What are attention masks?

• token_type_ids (Numpy array or tf.Tensor 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 token.

  What are token type IDs?

• position_ids (Numpy array or tf.Tensor 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].

  What are position IDs?

• head_mask (Numpy array or tf.Tensor 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 (tf.Tensor 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) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

• output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

• return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

• training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

• labels (tf.Tensor or np.ndarray 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

A TFSequenceClassifierOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (LayoutLMConfig) and inputs.

• loss (tf.Tensor of shape (batch_size, ), optional, returned when labels is provided) – Classification (or regression if config.num_labels==1) loss.

• logits (tf.Tensor of shape (batch_size, config.num_labels)) – Classification (or regression if config.num_labels==1) scores (before SoftMax).

• hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (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(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Examples:

>>> from transformers import LayoutLMTokenizer, TFLayoutLMForSequenceClassification
>>> import tensorflow as tf

>>> tokenizer = LayoutLMTokenizer.from_pretrained('microsoft/layoutlm-base-uncased')
>>> model = TFLayoutLMForSequenceClassification.from_pretrained('microsoft/layoutlm-base-uncased')

>>> words = ["Hello", "world"]
>>> normalized_word_boxes = [637, 773, 693, 782], [698, 773, 733, 782]

>>> token_boxes = []
>>> for word, box in zip(words, normalized_word_boxes):
...     word_tokens = tokenizer.tokenize(word)
...     token_boxes.extend([box] * len(word_tokens))
>>> # add bounding boxes of cls + sep tokens
>>> token_boxes = [[0, 0, 0, 0]] + token_boxes + [[1000, 1000, 1000, 1000]]

>>> encoding = tokenizer(' '.join(words), return_tensors="tf")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = tf.convert_to_tensor([token_boxes])
>>> sequence_label = tf.convert_to_tensor([1])

>>> outputs = model(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask, token_type_ids=token_type_ids,
...                 labels=sequence_label)

>>> loss = outputs.loss
>>> logits = outputs.logits

Return type

TFSequenceClassifierOutput or tuple(tf.Tensor)

serving_output(output: transformers.modeling_tf_outputs.TFSequenceClassifierOutput) → transformers.modeling_tf_outputs.TFSequenceClassifierOutput

Prepare the output of the saved model. Each model must implement this function.

Parameters

output (TFBaseModelOutput) – The output returned by the model.

TFLayoutLMForTokenClassification

class transformers.TFLayoutLMForTokenClassification(*args, **kwargs)

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.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

• having all inputs as keyword arguments (like PyTorch models), or

• having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

• a single Tensor with input_ids only and nothing else: model(inputs_ids)

• a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])

• a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

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 the from_pretrained() method to load the model weights.

call(input_ids: Optional[Union[List[tensorflow.python.framework.ops.Tensor], List[numpy.ndarray], Dict[str, tensorflow.python.framework.ops.Tensor], Dict[str, numpy.ndarray], numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, bbox: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, attention_mask: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, token_type_ids: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, position_ids: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, head_mask: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, inputs_embeds: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, labels: Optional[Union[numpy.ndarray, tensorflow.python.framework.ops.Tensor]] = None, training: Optional[bool] = False, **kwargs) → Union[transformers.modeling_tf_outputs.TFTokenClassifierOutput, Tuple[tensorflow.python.framework.ops.Tensor]]

The TFLayoutLMForTokenClassification 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 (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) –

  Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using LayoutLMTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

  What are input IDs?

• bbox (Numpy array or tf.Tensor of shape (batch_size, sequence_length, 4), optional) – Bounding Boxes of each input sequence tokens. Selected in the range [0, config.max_2d_position_embeddings- 1].

• attention_mask (Numpy array or tf.Tensor 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 tokens that are masked.

  What are attention masks?

• token_type_ids (Numpy array or tf.Tensor 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 token.

  What are token type IDs?

• position_ids (Numpy array or tf.Tensor 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].

  What are position IDs?

• head_mask (Numpy array or tf.Tensor 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 (tf.Tensor 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) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

• output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

• return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

• training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

• labels (tf.Tensor or np.ndarray of shape (batch_size, sequence_length), optional) – Labels for computing the token classification loss. Indices should be in [0, ..., config.num_labels - 1].

Returns

A TFTokenClassifierOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (LayoutLMConfig) and inputs.

• loss (tf.Tensor of shape (n,), optional, where n is the number of unmasked labels, returned when labels is provided) – Classification loss.

• logits (tf.Tensor of shape (batch_size, sequence_length, config.num_labels)) – Classification scores (before SoftMax).

• hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (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(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Examples:

>>> from transformers import LayoutLMTokenizer, TFLayoutLMForTokenClassification
>>> import torch

>>> tokenizer = LayoutLMTokenizer.from_pretrained('microsoft/layoutlm-base-uncased')
>>> model = TFLayoutLMForTokenClassification.from_pretrained('microsoft/layoutlm-base-uncased')

>>> words = ["Hello", "world"]
>>> normalized_word_boxes = [637, 773, 693, 782], [698, 773, 733, 782]

>>> token_boxes = []
>>> for word, box in zip(words, normalized_word_boxes):
...     word_tokens = tokenizer.tokenize(word)
...     token_boxes.extend([box] * len(word_tokens))
>>> # add bounding boxes of cls + sep tokens
>>> token_boxes = [[0, 0, 0, 0]] + token_boxes + [[1000, 1000, 1000, 1000]]

>>> encoding = tokenizer(' '.join(words), return_tensors="tf")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = tf.convert_to_tensor([token_boxes])
>>> token_labels = tf.convert_to_tensor([1,1,0,0])

>>> outputs = model(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask, token_type_ids=token_type_ids,
...                 labels=token_labels)

>>> loss = outputs.loss
>>> logits = outputs.logits

Return type

TFTokenClassifierOutput or tuple(tf.Tensor)

serving_output(output: transformers.modeling_tf_outputs.TFTokenClassifierOutput) → transformers.modeling_tf_outputs.TFTokenClassifierOutput

Prepare the output of the saved model. Each model must implement this function.

Parameters

output (TFBaseModelOutput) – The output returned by the model.