modeling

Modeling classes for LayoutLM model.

class LayoutLMModel(vocab_size, 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, layer_norm_eps=1e-12, max_position_embeddings=512, max_2d_position_embeddings=1024, type_vocab_size=16, initializer_range=0.02, pad_token_id=0, pool_act='tanh')[source]

Bases: paddlenlp.transformers.layoutlm.modeling.LayoutLMPretrainedModel

The bare LayoutLM Model outputting raw hidden-states.

This model inherits from PretrainedModel. Refer to the superclass documentation for the generic methods.

This model is also a Paddle paddle.nn.Layer subclass. Use it as a regular Paddle Layer and refer to the Paddle documentation for all matter related to general usage and behavior.

Parameters

  • vocab_size (int) – Vocabulary size of the LayoutLM model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling LayoutLMModel.

  • hidden_size (int) – Dimensionality of the encoder layers and the pooler layer.

  • num_hidden_layers (int) – Number of hidden layers in the Transformer encoder.

  • num_attention_heads (int) – Number of attention heads for each attention layer in the Transformer encoder.

  • intermediate_size (int) – Dimensionality of the “intermediate” (often named feed-forward) layer in the Transformer encoder.

  • hidden_act (str, optional) – The non-linear activation function in the feed-forward layer. "gelu", "relu" and any other paddle supported activation functions are supported.

  • hidden_dropout_prob (float) – The dropout probability for all fully connected layers in the embeddings and encoder.

  • attention_probs_dropout_prob (float) – The dropout probability for all fully connected layers in the pooler.

  • type_vocab_size (int, optional) – The vocabulary size of token_type_ids. Defaults to 16.

  • initializer_range (float) –

    The standard deviation of the normal initializer. Defaults to 0.02.

    Note

    A normal_initializer initializes weight matrices as normal distributions. See LayoutLMPretrainedModel.init_weights() for how weights are initialized in LayoutLMModel.

  • pad_token_id (int, optional) – The index of padding token in the token vocabulary. Defaults to 0.

  • pooled_act (str, optional) – The non-linear activation function in the pooling layer. Defaults to "tanh".

resize_position_embeddings(new_num_position_embeddings)[source]

Resizes position embeddings of the model if new_num_position_embeddings != config["max_position_embeddings"].

Parameters

new_num_position_embeddings (int) – The number of new position embedding matrix. If position embeddings are learned, increasing the size will add newly initialized vectors at the end, whereas reducing the size will remove vectors from the end.

forward(input_ids=None, bbox=None, token_type_ids=None, position_ids=None, attention_mask=None, output_hidden_states=False)[source]

The LayoutLMModel forward method, overrides the __call__() special method.

Parameters

  • input_ids (Tensor) – Indices of input sequence tokens in the vocabulary. They are numerical representations of tokens that build the input sequence. Its data type should be int64 and it has a shape of [batch_size, sequence_length].

  • token_type_ids (Tensor, optional) –

    Segment token indices to indicate different portions of the inputs. Selected in the range [0, type_vocab_size - 1]. If type_vocab_size is 2, which means the inputs have two portions. Indices can either be 0 or 1:

    • 0 corresponds to a sentence A token,

    • 1 corresponds to a sentence B token.

    Its data type should be int64 and it has a shape of [batch_size, sequence_length]. Defaults to None, which means we don’t add segment embeddings.

  • position_ids (Tensor, optional) – Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, max_position_embeddings - 1]. Shape as (batch_size, num_tokens) and dtype as int64. Defaults to None.

  • attention_mask (Tensor, optional) – Mask used in multi-head attention to avoid performing attention on to some unwanted positions, usually the paddings or the subsequent positions. Its data type can be int, float and bool. When the data type is bool, the masked tokens have False values and the others have True values. When the data type is int, the masked tokens have 0 values and the others have 1 values. When the data type is float, the masked tokens have -INF values and the others have 0 values. It is a tensor with shape broadcasted to [batch_size, num_attention_heads, sequence_length, sequence_length]. Defaults to None, which means nothing needed to be prevented attention to.

  • output_hidden_states (bool, optional) – Whether to return the output of each hidden layers. Defaults to False.

Returns

Returns tuple (sequence_output, pooled_output).

With the fields:

  • sequence_output (Tensor):

    Sequence of hidden-states at the last layer of the model. It’s data type should be float32 and its shape is [batch_size, sequence_length, hidden_size].

  • pooled_output (Tensor):

    The output of first token ([CLS]) in sequence. We “pool” the model by simply taking the hidden state corresponding to the first token. Its data type should be float32 and its shape is [batch_size, hidden_size].

Return type

tuple

class LayoutLMPretrainedModel(*args, **kwargs)[source]

Bases: paddlenlp.transformers.model_utils.PretrainedModel

init_weights(layer)[source]

Initialization hook

base_model_class

alias of paddlenlp.transformers.layoutlm.modeling.LayoutLMModel

class LayoutLMForMaskedLM(layoutlm)[source]

Bases: paddlenlp.transformers.layoutlm.modeling.LayoutLMPretrainedModel

LayoutLM Model with a masked language modeling head on top.

Parameters

layoutlm (LayoutLMModel) – An instance of LayoutLMModel.

resize_position_embeddings(new_num_position_embeddings)[source]

Resizes position embeddings of the model if new_num_position_embeddings != config["max_position_embeddings"].

Parameters

new_num_position_embeddings (int) – The number of new position embedding matrix. If position embeddings are learned, increasing the size will add newly initialized vectors at the end, whereas reducing the size will remove vectors from the end.

forward(input_ids, bbox=None, token_type_ids=None, position_ids=None, attention_mask=None)[source]
Parameters
Returns

Returns tensor prediction_scores, The scores of masked token prediction. Its data type should be float32 and shape is [batch_size, sequence_length, vocab_size].

Return type

Tensor

Example

import paddle
from paddlenlp.transformers import LayoutLMForMaskedLM, LayoutLMTokenizer

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

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}

logits = model(**inputs)
print(logits.shape)
class LayoutLMForTokenClassification(layoutlm, num_classes=2, dropout=None)[source]

Bases: paddlenlp.transformers.layoutlm.modeling.LayoutLMPretrainedModel

LayoutLM Model with a linear layer on top of the hidden-states output layer, designed for token classification tasks like NER tasks.

Parameters

  • layoutlm (LayoutLMModel) – An instance of LayoutLMModel.

  • num_classes (int, optional) – The number of classes. Defaults to 2.

  • dropout (float, optional) – The dropout probability for output of LayoutLM. If None, use the same value as hidden_dropout_prob of LayoutLMModel instance layoutlm. Defaults to None.

get_input_embeddings()[source]

get input embedding of model

Returns

embedding of model

Return type

nn.Embedding

resize_position_embeddings(new_num_position_embeddings)[source]

Resizes position embeddings of the model if new_num_position_embeddings != config["max_position_embeddings"].

Parameters

new_num_position_embeddings (int) – The number of new position embedding matrix. If position embeddings are learned, increasing the size will add newly initialized vectors at the end, whereas reducing the size will remove vectors from the end.

forward(input_ids, bbox=None, attention_mask=None, token_type_ids=None, position_ids=None, output_hidden_states=False)[source]

The LayoutLMForTokenClassification forward method, overrides the __call__() special method.

Parameters
Returns

Returns tensor logits, a tensor of the input token classification logits. Shape as [batch_size, sequence_length, num_classes] and dtype as float32.

Return type

Tensor

Example

import paddle
from paddlenlp.transformers import LayoutLMFForTokenClassification
from paddlenlp.transformers import LayoutLMFTokenizer

tokenizer = LayoutLMFTokenizer.from_pretrained('layoutlm-base-uncased')
model = LayoutLMFForTokenClassification.from_pretrained('layoutlm-base-uncased', num_classes=2)

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}

logits = model(**inputs)
print(logits.shape)
# [1, 13, 2]
class LayoutLMForSequenceClassification(layoutlm, num_classes=2)[source]

Bases: paddlenlp.transformers.layoutlm.modeling.LayoutLMPretrainedModel

LayoutLM Model with a linear layer on top of the output layer, designed for sequence classification/regression tasks like GLUE tasks.

Parameters

  • layoutlm (LayoutLMModel) – An instance of LayoutLMModel.

  • num_classes (int, optional) – The number of classes. Defaults to 2.

get_input_embeddings()[source]

get input embedding of model

Returns

embedding of model

Return type

nn.Embedding

resize_position_embeddings(new_num_position_embeddings)[source]

Resizes position embeddings of the model if new_num_position_embeddings != config["max_position_embeddings"].

Parameters

new_num_position_embeddings (int) – The number of new position embedding matrix. If position embeddings are learned, increasing the size will add newly initialized vectors at the end, whereas reducing the size will remove vectors from the end.

forward(input_ids, bbox=None, attention_mask=None, token_type_ids=None, position_ids=None, output_hidden_states=False)[source]

The LayoutLMForSequenceClassification forward method, overrides the __call__() special method.

Parameters
Returns

Returns tensor logits, a tensor of the input text classification logits. Shape as [batch_size, num_classes] and dtype as float32.

Return type

Tensor

Example

import paddle
from paddlenlp.transformers import LayoutLMForSequenceClassification
from paddlenlp.transformers import LayoutLMTokenizer

tokenizer = LayoutLMTokenizer.from_pretrained('layoutlm-base-uncased')
model = LayoutLMForSequenceClassification.from_pretrained('layoutlm-base-uncased', num_classes=2)

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}

logits = model(**inputs)
print(logits.shape)
# [1, 2]