modeling#
Modeling classes for LayoutLM model.
- class LayoutLMModel(config: LayoutLMConfig)[源代码]#
-
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.
- 参数:
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 to16
.initializer_range (float) --
The standard deviation of the normal initializer. Defaults to 0.02.
备注
A normal_initializer initializes weight matrices as normal distributions. See
LayoutLMPretrainedModel.init_weights()
for how weights are initialized inLayoutLMModel
.pad_token_id (int, optional) -- The index of padding token in the token vocabulary. Defaults to
0
.pool_act (str, optional) -- The non-linear activation function in the pooling layer. Defaults to
"tanh"
.
- set_input_embeddings(value)[源代码]#
set new input embedding for model
- 参数:
value (Embedding) -- the new embedding of model
- 抛出:
NotImplementedError -- Model has not implement
set_input_embeddings
method
- resize_position_embeddings(new_num_position_embeddings)[源代码]#
Resizes position embeddings of the model if
new_num_position_embeddings != config["max_position_embeddings"]
.- 参数:
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)[源代码]#
The LayoutLMModel forward method, overrides the
__call__()
special method.- 参数:
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]
. Iftype_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 toNone
, 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 toNone
.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 haveFalse
values and the others haveTrue
values. When the data type is int, themasked
tokens have0
values and the others have1
values. When the data type is float, themasked
tokens have-INF
values and the others have0
values. It is a tensor with shape broadcasted to[batch_size, num_attention_heads, sequence_length, sequence_length]
. Defaults toNone
, 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
.
- 返回:
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].
- 返回类型:
tuple
- class LayoutLMPretrainedModel(*args, **kwargs)[源代码]#
-
- config_class#
LayoutLMConfig
的别名
- base_model_class#
LayoutLMModel
的别名
- class LayoutLMForMaskedLM(config: LayoutLMConfig)[源代码]#
-
LayoutLM Model with a
masked language modeling
head on top.- 参数:
config (
LayoutLMConfig
) -- An instance of LayoutLMConfig used to construct LayoutLMForMaskedLM.
- resize_position_embeddings(new_num_position_embeddings)[源代码]#
Resizes position embeddings of the model if
new_num_position_embeddings != config["max_position_embeddings"]
.- 参数:
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)[源代码]#
- 参数:
input_ids (Tensor) -- See
LayoutLMModel
.bbox (Tensor) -- See
LayoutLMModel
.token_type_ids (Tensor, optional) -- See
LayoutLMModel
.position_ids (Tensor, optional) -- See
LayoutLMModel
.attention_mask (Tensor, optional) -- See
LayoutLMModel
.
- 返回:
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].- 返回类型:
Tensor
示例
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!", return_tensors="pd") logits = model(**inputs) print(logits.shape)
- class LayoutLMForTokenClassification(config: LayoutLMConfig)[源代码]#
-
LayoutLM Model with a linear layer on top of the hidden-states output layer, designed for token classification tasks like NER tasks.
- 参数:
config (
LayoutLMConfig
) -- An instance of LayoutLMConfig used to construct LayoutLMForTokenClassification.
- resize_position_embeddings(new_num_position_embeddings)[源代码]#
Resizes position embeddings of the model if
new_num_position_embeddings != config["max_position_embeddings"]
.- 参数:
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)[源代码]#
The LayoutLMForTokenClassification forward method, overrides the __call__() special method.
- 参数:
input_ids (Tensor) -- See
LayoutLMModel
.bbox (Tensor) -- See
LayoutLMModel
.attention_mask (list, optional) -- See
LayoutLMModel
.token_type_ids (Tensor, optional) -- See
LayoutLMModel
.position_ids (Tensor, optional) -- See
LayoutLMModel
.output_hidden_states (Tensor, optional) -- See
LayoutLMModel
.
- 返回:
Returns tensor
logits
, a tensor of the input token classification logits. Shape as[batch_size, sequence_length, num_classes]
and dtype asfloat32
.- 返回类型:
Tensor
示例
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!", return_tensors="pd") logits = model(**inputs) print(logits.shape) # [1, 13, 2]
- class LayoutLMForSequenceClassification(config: LayoutLMConfig)[源代码]#
-
LayoutLM Model with a linear layer on top of the output layer, designed for sequence classification/regression tasks like GLUE tasks.
- 参数:
config (
LayoutLMConfig
) -- An instance of LayoutLMConfig used to construct LayoutLMForSequenceClassification.
- resize_position_embeddings(new_num_position_embeddings)[源代码]#
Resizes position embeddings of the model if
new_num_position_embeddings != config["max_position_embeddings"]
.- 参数:
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)[源代码]#
The LayoutLMForSequenceClassification forward method, overrides the __call__() special method.
- 参数:
input_ids (Tensor) -- See
LayoutLMModel
.bbox (Tensor) -- See
LayoutLMModel
.attention_mask (list, optional) -- See
LayoutLMModel
.token_type_ids (Tensor, optional) -- See
LayoutLMModel
.position_ids (Tensor, optional) -- See
LayoutLMModel
.output_hidden_states (Tensor, optional) -- See
LayoutLMModel
.
- 返回:
Returns tensor
logits
, a tensor of the input text classification logits. Shape as[batch_size, num_classes]
and dtype as float32.- 返回类型:
Tensor
示例
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!", return_tensors="pd") logits = model(**inputs) print(logits.shape) # [1, 2]