modeling#
Modeling classes for LayoutLMv2 model.
- class LayoutLMv2Model(config)[source]#
Bases:
LayoutLMv2PretrainedModel
The bare LayoutLMv2 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 XLNet model. Defines the number of different tokens that can be represented by theinputs_ids
passed when calling XLNetModel.hidden_size (
int
, optional) – Dimensionality of the encoder layers and the pooler layer. Defaults to768
.num_hidden_layers (
int
, optional) – Number of hidden layers in the Transformer encoder. Defaults to12
.num_attention_heads (
int
, optional) – Number of attention heads for each attention layer in the Transformer encoder. Defaults to12
.intermediate_size (
int
, optional) – Dimensionality of the “intermediate” (often named feed-forward) layer in the Transformer encoder. Defaults to3072
.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. Defaults to"gelu"
.hidden_dropout_prob (
float
, optional) – The dropout probability for all fully connected layers in the embeddings and encoder. Defaults to0.1
.attention_probs_dropout_prob (
float
, optional) – The dropout probability for all fully connected layers in the pooler. Defaults to0.1
.initializer_range (
float
, optional) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Defaults to0.02
.
- 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, image=None, token_type_ids=None, position_ids=None, attention_mask=None, head_mask=None, output_hidden_states=False, output_attentions=False)[source]#
Defines the computation performed at every call. Should be overridden by all subclasses.
- Parameters:
*inputs (tuple) – unpacked tuple arguments
**kwargs (dict) – unpacked dict arguments
- class LayoutLMv2PretrainedModel(*args, **kwargs)[source]#
Bases:
PretrainedModel
- config_class#
alias of
LayoutLMv2Config
- base_model_class#
alias of
LayoutLMv2Model
- class LayoutLMv2ForTokenClassification(config)[source]#
Bases:
LayoutLMv2PretrainedModel
- 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=None, bbox=None, image=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, labels=None)[source]#
Defines the computation performed at every call. Should be overridden by all subclasses.
- Parameters:
*inputs (tuple) – unpacked tuple arguments
**kwargs (dict) – unpacked dict arguments
- class LayoutLMv2ForPretraining(config)[source]#
Bases:
LayoutLMv2PretrainedModel
- 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, image=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, masked_positions=None)[source]#
Defines the computation performed at every call. Should be overridden by all subclasses.
- Parameters:
*inputs (tuple) – unpacked tuple arguments
**kwargs (dict) – unpacked dict arguments
- class LayoutLMv2ForRelationExtraction(config)[source]#
Bases:
LayoutLMv2PretrainedModel
- 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, labels=None, image=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, entities=None, relations=None)[source]#
Defines the computation performed at every call. Should be overridden by all subclasses.
- Parameters:
*inputs (tuple) – unpacked tuple arguments
**kwargs (dict) – unpacked dict arguments