layoutlm

mindnlp.transformers.models.layoutlm.modeling_layoutlm

MindSpore LayoutLM model.

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMEmbeddings

Bases: Module

Construct the embeddings from word, position and token_type embeddings.

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

class LayoutLMEmbeddings(nn.Module):
    """Construct the embeddings from word, position and token_type embeddings."""

    def __init__(self, config):
        super(LayoutLMEmbeddings, self).__init__()
        self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=config.pad_token_id)
        self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size)
        self.x_position_embeddings = nn.Embedding(config.max_2d_position_embeddings, config.hidden_size)
        self.y_position_embeddings = nn.Embedding(config.max_2d_position_embeddings, config.hidden_size)
        self.h_position_embeddings = nn.Embedding(config.max_2d_position_embeddings, config.hidden_size)
        self.w_position_embeddings = nn.Embedding(config.max_2d_position_embeddings, config.hidden_size)
        self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size)

        self.LayerNorm = LayoutLMLayerNorm(config.hidden_size, eps=config.layer_norm_eps)
        self.dropout = nn.Dropout(config.hidden_dropout_prob)

        self.register_buffer(
            "position_ids", ops.arange(config.max_position_embeddings).expand((1, -1)), persistent=False
        )

    def forward(
        self,
        input_ids=None,
        bbox=None,
        token_type_ids=None,
        position_ids=None,
        inputs_embeds=None,
    ):
        if input_ids is not None:
            input_shape = input_ids.shape
        else:
            input_shape = inputs_embeds.shape[:-1]

        seq_length = input_shape[1]

        if position_ids is None:
            position_ids = self.position_ids[:, :seq_length]

        if token_type_ids is None:
            token_type_ids = ops.zeros(input_shape, dtype=mindspore.int64)

        if inputs_embeds is None:
            inputs_embeds = self.word_embeddings(input_ids)

        words_embeddings = inputs_embeds
        position_embeddings = self.position_embeddings(position_ids)
        try:
            left_position_embeddings = self.x_position_embeddings(bbox[:, :, 0])
            upper_position_embeddings = self.y_position_embeddings(bbox[:, :, 1])
            right_position_embeddings = self.x_position_embeddings(bbox[:, :, 2])
            lower_position_embeddings = self.y_position_embeddings(bbox[:, :, 3])
        except IndexError as e:
            raise IndexError("The `bbox`coordinate values should be within 0-1000 range.") from e

        h_position_embeddings = self.h_position_embeddings(bbox[:, :, 3] - bbox[:, :, 1])
        w_position_embeddings = self.w_position_embeddings(bbox[:, :, 2] - bbox[:, :, 0])
        token_type_embeddings = self.token_type_embeddings(token_type_ids)

        embeddings = (
            words_embeddings
            + position_embeddings
            + left_position_embeddings
            + upper_position_embeddings
            + right_position_embeddings
            + lower_position_embeddings
            + h_position_embeddings
            + w_position_embeddings
            + token_type_embeddings
        )
        embeddings = self.LayerNorm(embeddings)
        embeddings = self.dropout(embeddings)
        return embeddings

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMForMaskedLM

Bases: LayoutLMPreTrainedModel

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

class LayoutLMForMaskedLM(LayoutLMPreTrainedModel):
    _tied_weights_keys = ["cls.predictions.decoder.bias", "cls.predictions.decoder.weight"]

    def __init__(self, config):
        super().__init__(config)

        self.layoutlm = LayoutLMModel(config)
        self.cls = LayoutLMOnlyMLMHead(config)

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.layoutlm.embeddings.word_embeddings

    def get_output_embeddings(self):
        return self.cls.predictions.decoder

    def set_output_embeddings(self, new_embeddings):
        self.cls.predictions.decoder = new_embeddings
        self.cls.predictions.bias = new_embeddings.bias

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        bbox: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        encoder_hidden_states: Optional[mindspore.Tensor] = None,
        encoder_attention_mask: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, MaskedLMOutput]:
        r"""
        labels (`mindspore.Tensor` 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:

        Examples:

        ```python
        >>> from transformers import AutoTokenizer, LayoutLMForMaskedLM
        >>> import torch

        >>> tokenizer = AutoTokenizer.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="ms")
        >>> input_ids = encoding["input_ids"]
        >>> attention_mask = encoding["attention_mask"]
        >>> token_type_ids = encoding["token_type_ids"]
        >>> bbox = mindspore.tensor([token_boxes])

        >>> labels = tokenizer("Hello world", return_tensors="ms")["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_dict = return_dict if return_dict is not None else self.config.use_return_dict

        outputs = self.layoutlm(
            input_ids,
            bbox,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]
        prediction_scores = self.cls(sequence_output)

        masked_lm_loss = None
        if labels is not None:
            loss_fct = CrossEntropyLoss()
            masked_lm_loss = loss_fct(
                prediction_scores.view(-1, self.config.vocab_size),
                labels.view(-1),
            )

        if not return_dict:
            output = (prediction_scores,) + outputs[2:]
            return ((masked_lm_loss,) + output) if masked_lm_loss is not None else output

        return MaskedLMOutput(
            loss=masked_lm_loss,
            logits=prediction_scores,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMForMaskedLM.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)

labels (mindspore.Tensor 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:

Examples:

>>> from transformers import AutoTokenizer, LayoutLMForMaskedLM
>>> import torch

>>> tokenizer = AutoTokenizer.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="ms")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = mindspore.tensor([token_boxes])

>>> labels = tokenizer("Hello world", return_tensors="ms")["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

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    bbox: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    encoder_hidden_states: Optional[mindspore.Tensor] = None,
    encoder_attention_mask: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, MaskedLMOutput]:
    r"""
    labels (`mindspore.Tensor` 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:

    Examples:

    ```python
    >>> from transformers import AutoTokenizer, LayoutLMForMaskedLM
    >>> import torch

    >>> tokenizer = AutoTokenizer.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="ms")
    >>> input_ids = encoding["input_ids"]
    >>> attention_mask = encoding["attention_mask"]
    >>> token_type_ids = encoding["token_type_ids"]
    >>> bbox = mindspore.tensor([token_boxes])

    >>> labels = tokenizer("Hello world", return_tensors="ms")["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_dict = return_dict if return_dict is not None else self.config.use_return_dict

    outputs = self.layoutlm(
        input_ids,
        bbox,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        encoder_hidden_states=encoder_hidden_states,
        encoder_attention_mask=encoder_attention_mask,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    sequence_output = outputs[0]
    prediction_scores = self.cls(sequence_output)

    masked_lm_loss = None
    if labels is not None:
        loss_fct = CrossEntropyLoss()
        masked_lm_loss = loss_fct(
            prediction_scores.view(-1, self.config.vocab_size),
            labels.view(-1),
        )

    if not return_dict:
        output = (prediction_scores,) + outputs[2:]
        return ((masked_lm_loss,) + output) if masked_lm_loss is not None else output

    return MaskedLMOutput(
        loss=masked_lm_loss,
        logits=prediction_scores,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMForQuestionAnswering

Bases: LayoutLMPreTrainedModel

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

class LayoutLMForQuestionAnswering(LayoutLMPreTrainedModel):
    def __init__(self, config, has_visual_segment_embedding=True):
        super().__init__(config)
        self.num_labels = config.num_labels

        self.layoutlm = LayoutLMModel(config)
        self.qa_outputs = nn.Linear(config.hidden_size, config.num_labels)

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.layoutlm.embeddings.word_embeddings

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        bbox: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        start_positions: Optional[mindspore.Tensor] = None,
        end_positions: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, QuestionAnsweringModelOutput]:
        r"""
        start_positions (`mindspore.Tensor` of shape `(batch_size,)`, *optional*):
            Labels for position (index) of the start of the labelled span for computing the token classification loss.
            Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
            are not taken into account for computing the loss.
        end_positions (`mindspore.Tensor` of shape `(batch_size,)`, *optional*):
            Labels for position (index) of the end of the labelled span for computing the token classification loss.
            Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
            are not taken into account for computing the loss.

        Returns:

        Example:

        In the example below, we prepare a question + context pair for the LayoutLM model. It will give us a prediction
        of what it thinks the answer is (the span of the answer within the texts parsed from the image).

        ```python
        >>> from transformers import AutoTokenizer, LayoutLMForQuestionAnswering
        >>> from datasets import load_dataset
        >>> import torch

        >>> tokenizer = AutoTokenizer.from_pretrained("impira/layoutlm-document-qa", add_prefix_space=True)
        >>> model = LayoutLMForQuestionAnswering.from_pretrained("impira/layoutlm-document-qa", revision="1e3ebac")

        >>> dataset = load_dataset("nielsr/funsd", split="train", trust_remote_code=True)
        >>> example = dataset[0]
        >>> question = "what's his name?"
        >>> words = example["words"]
        >>> boxes = example["bboxes"]

        >>> encoding = tokenizer(
        ...     question.split(), words, is_split_into_words=True, return_token_type_ids=True, return_tensors="ms"
        ... )
        >>> bbox = []
        >>> for i, s, w in zip(encoding.input_ids[0], encoding.sequence_ids(0), encoding.word_ids(0)):
        ...     if s == 1:
        ...         bbox.append(boxes[w])
        ...     elif i == tokenizer.sep_token_id:
        ...         bbox.append([1000] * 4)
        ...     else:
        ...         bbox.append([0] * 4)
        >>> encoding["bbox"] = mindspore.tensor([bbox])

        >>> word_ids = encoding.word_ids(0)
        >>> outputs = model(**encoding)
        >>> loss = outputs.loss
        >>> start_scores = outputs.start_logits
        >>> end_scores = outputs.end_logits
        >>> start, end = word_ids[start_scores.argmax(-1)], word_ids[end_scores.argmax(-1)]
        >>> print(" ".join(words[start : end + 1]))
        M. Hamann P. Harper, P. Martinez
        ```"""

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        outputs = self.layoutlm(
            input_ids=input_ids,
            bbox=bbox,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]

        logits = self.qa_outputs(sequence_output)
        start_logits, end_logits = ops.split(logits, 1, dim=-1)
        start_logits = start_logits.squeeze(-1)
        end_logits = end_logits.squeeze(-1)

        total_loss = None
        if start_positions is not None and end_positions is not None:
            # If we are on multi-GPU, split add a dimension
            if len(start_positions.shape) > 1:
                start_positions = start_positions.squeeze(-1)
            if len(end_positions.shape) > 1:
                end_positions = end_positions.squeeze(-1)
            # sometimes the start/end positions are outside our model inputs, we ignore these terms
            ignored_index = start_logits.shape[1]
            start_positions = start_positions.clamp(0, ignored_index)
            end_positions = end_positions.clamp(0, ignored_index)

            loss_fct = CrossEntropyLoss(ignore_index=ignored_index)
            start_loss = loss_fct(start_logits, start_positions)
            end_loss = loss_fct(end_logits, end_positions)
            total_loss = (start_loss + end_loss) / 2

        if not return_dict:
            output = (start_logits, end_logits) + outputs[2:]
            return ((total_loss,) + output) if total_loss is not None else output

        return QuestionAnsweringModelOutput(
            loss=total_loss,
            start_logits=start_logits,
            end_logits=end_logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMForQuestionAnswering.forward(input_ids=None, bbox=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, start_positions=None, end_positions=None, output_attentions=None, output_hidden_states=None, return_dict=None)

start_positions (mindspore.Tensor of shape (batch_size,), optional): Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss. end_positions (mindspore.Tensor of shape (batch_size,), optional): Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.

Returns:

Example:

In the example below, we prepare a question + context pair for the LayoutLM model. It will give us a prediction of what it thinks the answer is (the span of the answer within the texts parsed from the image).

>>> from transformers import AutoTokenizer, LayoutLMForQuestionAnswering
>>> from datasets import load_dataset
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("impira/layoutlm-document-qa", add_prefix_space=True)
>>> model = LayoutLMForQuestionAnswering.from_pretrained("impira/layoutlm-document-qa", revision="1e3ebac")

>>> dataset = load_dataset("nielsr/funsd", split="train", trust_remote_code=True)
>>> example = dataset[0]
>>> question = "what's his name?"
>>> words = example["words"]
>>> boxes = example["bboxes"]

>>> encoding = tokenizer(
...     question.split(), words, is_split_into_words=True, return_token_type_ids=True, return_tensors="ms"
... )
>>> bbox = []
>>> for i, s, w in zip(encoding.input_ids[0], encoding.sequence_ids(0), encoding.word_ids(0)):
...     if s == 1:
...         bbox.append(boxes[w])
...     elif i == tokenizer.sep_token_id:
...         bbox.append([1000] * 4)
...     else:
...         bbox.append([0] * 4)
>>> encoding["bbox"] = mindspore.tensor([bbox])

>>> word_ids = encoding.word_ids(0)
>>> outputs = model(**encoding)
>>> loss = outputs.loss
>>> start_scores = outputs.start_logits
>>> end_scores = outputs.end_logits
>>> start, end = word_ids[start_scores.argmax(-1)], word_ids[end_scores.argmax(-1)]
>>> print(" ".join(words[start : end + 1]))
M. Hamann P. Harper, P. Martinez

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    bbox: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    start_positions: Optional[mindspore.Tensor] = None,
    end_positions: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, QuestionAnsweringModelOutput]:
    r"""
    start_positions (`mindspore.Tensor` of shape `(batch_size,)`, *optional*):
        Labels for position (index) of the start of the labelled span for computing the token classification loss.
        Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
        are not taken into account for computing the loss.
    end_positions (`mindspore.Tensor` of shape `(batch_size,)`, *optional*):
        Labels for position (index) of the end of the labelled span for computing the token classification loss.
        Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
        are not taken into account for computing the loss.

    Returns:

    Example:

    In the example below, we prepare a question + context pair for the LayoutLM model. It will give us a prediction
    of what it thinks the answer is (the span of the answer within the texts parsed from the image).

    ```python
    >>> from transformers import AutoTokenizer, LayoutLMForQuestionAnswering
    >>> from datasets import load_dataset
    >>> import torch

    >>> tokenizer = AutoTokenizer.from_pretrained("impira/layoutlm-document-qa", add_prefix_space=True)
    >>> model = LayoutLMForQuestionAnswering.from_pretrained("impira/layoutlm-document-qa", revision="1e3ebac")

    >>> dataset = load_dataset("nielsr/funsd", split="train", trust_remote_code=True)
    >>> example = dataset[0]
    >>> question = "what's his name?"
    >>> words = example["words"]
    >>> boxes = example["bboxes"]

    >>> encoding = tokenizer(
    ...     question.split(), words, is_split_into_words=True, return_token_type_ids=True, return_tensors="ms"
    ... )
    >>> bbox = []
    >>> for i, s, w in zip(encoding.input_ids[0], encoding.sequence_ids(0), encoding.word_ids(0)):
    ...     if s == 1:
    ...         bbox.append(boxes[w])
    ...     elif i == tokenizer.sep_token_id:
    ...         bbox.append([1000] * 4)
    ...     else:
    ...         bbox.append([0] * 4)
    >>> encoding["bbox"] = mindspore.tensor([bbox])

    >>> word_ids = encoding.word_ids(0)
    >>> outputs = model(**encoding)
    >>> loss = outputs.loss
    >>> start_scores = outputs.start_logits
    >>> end_scores = outputs.end_logits
    >>> start, end = word_ids[start_scores.argmax(-1)], word_ids[end_scores.argmax(-1)]
    >>> print(" ".join(words[start : end + 1]))
    M. Hamann P. Harper, P. Martinez
    ```"""

    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    outputs = self.layoutlm(
        input_ids=input_ids,
        bbox=bbox,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    sequence_output = outputs[0]

    logits = self.qa_outputs(sequence_output)
    start_logits, end_logits = ops.split(logits, 1, dim=-1)
    start_logits = start_logits.squeeze(-1)
    end_logits = end_logits.squeeze(-1)

    total_loss = None
    if start_positions is not None and end_positions is not None:
        # If we are on multi-GPU, split add a dimension
        if len(start_positions.shape) > 1:
            start_positions = start_positions.squeeze(-1)
        if len(end_positions.shape) > 1:
            end_positions = end_positions.squeeze(-1)
        # sometimes the start/end positions are outside our model inputs, we ignore these terms
        ignored_index = start_logits.shape[1]
        start_positions = start_positions.clamp(0, ignored_index)
        end_positions = end_positions.clamp(0, ignored_index)

        loss_fct = CrossEntropyLoss(ignore_index=ignored_index)
        start_loss = loss_fct(start_logits, start_positions)
        end_loss = loss_fct(end_logits, end_positions)
        total_loss = (start_loss + end_loss) / 2

    if not return_dict:
        output = (start_logits, end_logits) + outputs[2:]
        return ((total_loss,) + output) if total_loss is not None else output

    return QuestionAnsweringModelOutput(
        loss=total_loss,
        start_logits=start_logits,
        end_logits=end_logits,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMForSequenceClassification

Bases: LayoutLMPreTrainedModel

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

class LayoutLMForSequenceClassification(LayoutLMPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels
        self.layoutlm = LayoutLMModel(config)
        self.dropout = nn.Dropout(config.hidden_dropout_prob)
        self.classifier = nn.Linear(config.hidden_size, config.num_labels)

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.layoutlm.embeddings.word_embeddings

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        bbox: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, SequenceClassifierOutput]:
        r"""
        labels (`mindspore.Tensor` 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:

        Examples:

        ```python
        >>> from transformers import AutoTokenizer, LayoutLMForSequenceClassification
        >>> import torch

        >>> tokenizer = AutoTokenizer.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="ms")
        >>> input_ids = encoding["input_ids"]
        >>> attention_mask = encoding["attention_mask"]
        >>> token_type_ids = encoding["token_type_ids"]
        >>> bbox = mindspore.tensor([token_boxes])
        >>> sequence_label = mindspore.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_dict = return_dict if return_dict is not None else self.config.use_return_dict

        outputs = self.layoutlm(
            input_ids=input_ids,
            bbox=bbox,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        pooled_output = outputs[1]

        pooled_output = self.dropout(pooled_output)
        logits = self.classifier(pooled_output)

        loss = None
        if labels is not None:
            if self.config.problem_type is None:
                if self.num_labels == 1:
                    self.config.problem_type = "regression"
                elif self.num_labels > 1 and labels.dtype in (mindspore.int64, mindspore.int32):
                    self.config.problem_type = "single_label_classification"
                else:
                    self.config.problem_type = "multi_label_classification"

            if self.config.problem_type == "regression":
                loss_fct = MSELoss()
                if self.num_labels == 1:
                    loss = loss_fct(logits.squeeze(), labels.squeeze())
                else:
                    loss = loss_fct(logits, labels)
            elif self.config.problem_type == "single_label_classification":
                loss_fct = CrossEntropyLoss()
                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
            elif self.config.problem_type == "multi_label_classification":
                loss_fct = BCEWithLogitsLoss()
                loss = loss_fct(logits, labels)
        if not return_dict:
            output = (logits,) + outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return SequenceClassifierOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMForSequenceClassification.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)

labels (mindspore.Tensor 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:

Examples:

>>> from transformers import AutoTokenizer, LayoutLMForSequenceClassification
>>> import torch

>>> tokenizer = AutoTokenizer.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="ms")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = mindspore.tensor([token_boxes])
>>> sequence_label = mindspore.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

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    bbox: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, SequenceClassifierOutput]:
    r"""
    labels (`mindspore.Tensor` 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:

    Examples:

    ```python
    >>> from transformers import AutoTokenizer, LayoutLMForSequenceClassification
    >>> import torch

    >>> tokenizer = AutoTokenizer.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="ms")
    >>> input_ids = encoding["input_ids"]
    >>> attention_mask = encoding["attention_mask"]
    >>> token_type_ids = encoding["token_type_ids"]
    >>> bbox = mindspore.tensor([token_boxes])
    >>> sequence_label = mindspore.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_dict = return_dict if return_dict is not None else self.config.use_return_dict

    outputs = self.layoutlm(
        input_ids=input_ids,
        bbox=bbox,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    pooled_output = outputs[1]

    pooled_output = self.dropout(pooled_output)
    logits = self.classifier(pooled_output)

    loss = None
    if labels is not None:
        if self.config.problem_type is None:
            if self.num_labels == 1:
                self.config.problem_type = "regression"
            elif self.num_labels > 1 and labels.dtype in (mindspore.int64, mindspore.int32):
                self.config.problem_type = "single_label_classification"
            else:
                self.config.problem_type = "multi_label_classification"

        if self.config.problem_type == "regression":
            loss_fct = MSELoss()
            if self.num_labels == 1:
                loss = loss_fct(logits.squeeze(), labels.squeeze())
            else:
                loss = loss_fct(logits, labels)
        elif self.config.problem_type == "single_label_classification":
            loss_fct = CrossEntropyLoss()
            loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
        elif self.config.problem_type == "multi_label_classification":
            loss_fct = BCEWithLogitsLoss()
            loss = loss_fct(logits, labels)
    if not return_dict:
        output = (logits,) + outputs[2:]
        return ((loss,) + output) if loss is not None else output

    return SequenceClassifierOutput(
        loss=loss,
        logits=logits,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMForTokenClassification

Bases: LayoutLMPreTrainedModel

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

class LayoutLMForTokenClassification(LayoutLMPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels
        self.layoutlm = LayoutLMModel(config)
        self.dropout = nn.Dropout(config.hidden_dropout_prob)
        self.classifier = nn.Linear(config.hidden_size, config.num_labels)

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.layoutlm.embeddings.word_embeddings

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        bbox: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, TokenClassifierOutput]:
        r"""
        labels (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.

        Returns:

        Examples:

        ```python
        >>> from transformers import AutoTokenizer, LayoutLMForTokenClassification
        >>> import torch

        >>> tokenizer = AutoTokenizer.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="ms")
        >>> input_ids = encoding["input_ids"]
        >>> attention_mask = encoding["attention_mask"]
        >>> token_type_ids = encoding["token_type_ids"]
        >>> bbox = mindspore.tensor([token_boxes])
        >>> token_labels = mindspore.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_dict = return_dict if return_dict is not None else self.config.use_return_dict

        outputs = self.layoutlm(
            input_ids=input_ids,
            bbox=bbox,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]

        sequence_output = self.dropout(sequence_output)
        logits = self.classifier(sequence_output)

        loss = None
        if labels is not None:
            loss_fct = CrossEntropyLoss()
            loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))

        if not return_dict:
            output = (logits,) + outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return TokenClassifierOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMForTokenClassification.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)

labels (mindspore.Tensor of shape (batch_size, sequence_length), optional): Labels for computing the token classification loss. Indices should be in [0, ..., config.num_labels - 1].

Returns:

Examples:

>>> from transformers import AutoTokenizer, LayoutLMForTokenClassification
>>> import torch

>>> tokenizer = AutoTokenizer.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="ms")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = mindspore.tensor([token_boxes])
>>> token_labels = mindspore.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

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    bbox: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, TokenClassifierOutput]:
    r"""
    labels (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
        Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.

    Returns:

    Examples:

    ```python
    >>> from transformers import AutoTokenizer, LayoutLMForTokenClassification
    >>> import torch

    >>> tokenizer = AutoTokenizer.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="ms")
    >>> input_ids = encoding["input_ids"]
    >>> attention_mask = encoding["attention_mask"]
    >>> token_type_ids = encoding["token_type_ids"]
    >>> bbox = mindspore.tensor([token_boxes])
    >>> token_labels = mindspore.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_dict = return_dict if return_dict is not None else self.config.use_return_dict

    outputs = self.layoutlm(
        input_ids=input_ids,
        bbox=bbox,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    sequence_output = outputs[0]

    sequence_output = self.dropout(sequence_output)
    logits = self.classifier(sequence_output)

    loss = None
    if labels is not None:
        loss_fct = CrossEntropyLoss()
        loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))

    if not return_dict:
        output = (logits,) + outputs[2:]
        return ((loss,) + output) if loss is not None else output

    return TokenClassifierOutput(
        loss=loss,
        logits=logits,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMModel

Bases: LayoutLMPreTrainedModel

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

class LayoutLMModel(LayoutLMPreTrainedModel):
    def __init__(self, config):
        super(LayoutLMModel, self).__init__(config)
        self.config = config

        self.embeddings = LayoutLMEmbeddings(config)
        self.encoder = LayoutLMEncoder(config)
        self.pooler = LayoutLMPooler(config)

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.embeddings.word_embeddings

    def set_input_embeddings(self, value):
        self.embeddings.word_embeddings = value

    def _prune_heads(self, heads_to_prune):
        """
        Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base
        class PreTrainedModel
        """
        for layer, heads in heads_to_prune.items():
            self.encoder.layer[layer].attention.prune_heads(heads)

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        bbox: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        encoder_hidden_states: Optional[mindspore.Tensor] = None,
        encoder_attention_mask: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, BaseModelOutputWithPoolingAndCrossAttentions]:
        r"""
        Returns:

        Examples:

        ```python
        >>> from transformers import AutoTokenizer, LayoutLMModel
        >>> import torch

        >>> tokenizer = AutoTokenizer.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="ms")
        >>> input_ids = encoding["input_ids"]
        >>> attention_mask = encoding["attention_mask"]
        >>> token_type_ids = encoding["token_type_ids"]
        >>> bbox = mindspore.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
        ```"""
        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if input_ids is not None and inputs_embeds is not None:
            raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
        elif input_ids is not None:
            self.warn_if_padding_and_no_attention_mask(input_ids, attention_mask)
            input_shape = input_ids.shape
        elif inputs_embeds is not None:
            input_shape = inputs_embeds.shape[:-1]
        else:
            raise ValueError("You have to specify either input_ids or inputs_embeds")

        if attention_mask is None:
            attention_mask = ops.ones(input_shape)
        if token_type_ids is None:
            token_type_ids = ops.zeros(input_shape, dtype=mindspore.int64)

        if bbox is None:
            bbox = ops.zeros(input_shape + (4,), dtype=mindspore.int64)

        extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)

        extended_attention_mask = extended_attention_mask.to(dtype=self.dtype)
        extended_attention_mask = (1.0 - extended_attention_mask) * float(ops.finfo(self.dtype).min)

        if head_mask is not None:
            if head_mask.dim() == 1:
                head_mask = head_mask.unsqueeze(0).unsqueeze(0).unsqueeze(-1).unsqueeze(-1)
                head_mask = head_mask.expand(self.config.num_hidden_layers, -1, -1, -1, -1)
            elif head_mask.dim() == 2:
                head_mask = head_mask.unsqueeze(1).unsqueeze(-1).unsqueeze(-1)
            head_mask = head_mask.to(dtype=next(self.parameters()).dtype)
        else:
            head_mask = [None] * self.config.num_hidden_layers

        embedding_output = self.embeddings(
            input_ids=input_ids,
            bbox=bbox,
            position_ids=position_ids,
            token_type_ids=token_type_ids,
            inputs_embeds=inputs_embeds,
        )
        encoder_outputs = self.encoder(
            embedding_output,
            extended_attention_mask,
            head_mask=head_mask,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        sequence_output = encoder_outputs[0]
        pooled_output = self.pooler(sequence_output)

        if not return_dict:
            return (sequence_output, pooled_output) + encoder_outputs[1:]

        return BaseModelOutputWithPoolingAndCrossAttentions(
            last_hidden_state=sequence_output,
            pooler_output=pooled_output,
            hidden_states=encoder_outputs.hidden_states,
            attentions=encoder_outputs.attentions,
            cross_attentions=encoder_outputs.cross_attentions,
        )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMModel.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)

Examples:

>>> from transformers import AutoTokenizer, LayoutLMModel
>>> import torch

>>> tokenizer = AutoTokenizer.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="ms")
>>> input_ids = encoding["input_ids"]
>>> attention_mask = encoding["attention_mask"]
>>> token_type_ids = encoding["token_type_ids"]
>>> bbox = mindspore.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

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    bbox: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    encoder_hidden_states: Optional[mindspore.Tensor] = None,
    encoder_attention_mask: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, BaseModelOutputWithPoolingAndCrossAttentions]:
    r"""
    Returns:

    Examples:

    ```python
    >>> from transformers import AutoTokenizer, LayoutLMModel
    >>> import torch

    >>> tokenizer = AutoTokenizer.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="ms")
    >>> input_ids = encoding["input_ids"]
    >>> attention_mask = encoding["attention_mask"]
    >>> token_type_ids = encoding["token_type_ids"]
    >>> bbox = mindspore.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
    ```"""
    output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
    output_hidden_states = (
        output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
    )
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    if input_ids is not None and inputs_embeds is not None:
        raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
    elif input_ids is not None:
        self.warn_if_padding_and_no_attention_mask(input_ids, attention_mask)
        input_shape = input_ids.shape
    elif inputs_embeds is not None:
        input_shape = inputs_embeds.shape[:-1]
    else:
        raise ValueError("You have to specify either input_ids or inputs_embeds")

    if attention_mask is None:
        attention_mask = ops.ones(input_shape)
    if token_type_ids is None:
        token_type_ids = ops.zeros(input_shape, dtype=mindspore.int64)

    if bbox is None:
        bbox = ops.zeros(input_shape + (4,), dtype=mindspore.int64)

    extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)

    extended_attention_mask = extended_attention_mask.to(dtype=self.dtype)
    extended_attention_mask = (1.0 - extended_attention_mask) * float(ops.finfo(self.dtype).min)

    if head_mask is not None:
        if head_mask.dim() == 1:
            head_mask = head_mask.unsqueeze(0).unsqueeze(0).unsqueeze(-1).unsqueeze(-1)
            head_mask = head_mask.expand(self.config.num_hidden_layers, -1, -1, -1, -1)
        elif head_mask.dim() == 2:
            head_mask = head_mask.unsqueeze(1).unsqueeze(-1).unsqueeze(-1)
        head_mask = head_mask.to(dtype=next(self.parameters()).dtype)
    else:
        head_mask = [None] * self.config.num_hidden_layers

    embedding_output = self.embeddings(
        input_ids=input_ids,
        bbox=bbox,
        position_ids=position_ids,
        token_type_ids=token_type_ids,
        inputs_embeds=inputs_embeds,
    )
    encoder_outputs = self.encoder(
        embedding_output,
        extended_attention_mask,
        head_mask=head_mask,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )
    sequence_output = encoder_outputs[0]
    pooled_output = self.pooler(sequence_output)

    if not return_dict:
        return (sequence_output, pooled_output) + encoder_outputs[1:]

    return BaseModelOutputWithPoolingAndCrossAttentions(
        last_hidden_state=sequence_output,
        pooler_output=pooled_output,
        hidden_states=encoder_outputs.hidden_states,
        attentions=encoder_outputs.attentions,
        cross_attentions=encoder_outputs.cross_attentions,
    )

mindnlp.transformers.models.layoutlm.modeling_layoutlm.LayoutLMPreTrainedModel

Bases: PreTrainedModel

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

Source code in mindnlp\transformers\models\layoutlm\modeling_layoutlm.py

class LayoutLMPreTrainedModel(PreTrainedModel):
    """
    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
    models.
    """

    config_class = LayoutLMConfig
    base_model_prefix = "layoutlm"
    supports_gradient_checkpointing = True

    def _init_weights(self, module):
        """Initialize the weights"""
        if isinstance(module, nn.Linear):
            # Slightly different from the TF version which uses truncated_normal for initialization
            nn.init.normal_(module.weight, mean=0.0, std=self.config.initializer_range)
            if module.bias is not None:
                nn.init.zeros_(module.bias)
        elif isinstance(module, nn.Embedding):
            nn.init.normal_(module.weight, mean=0.0, std=self.config.initializer_range)
            if module.padding_idx is not None:
                module.weight[module.padding_idx] = 0
        elif isinstance(module, LayoutLMLayerNorm):
            nn.init.zeros_(module.bias)
            nn.init.ones_(module.weight)

mindnlp.transformers.models.layoutlm.configuration_layoutlm

LayoutLM Models config

mindnlp.transformers.models.layoutlm.configuration_layoutlm.LayoutLMConfig

Bases: PretrainedConfig

LayoutLMConfig

Source code in mindnlp\transformers\models\layoutlm\configuration_layoutlm.py

class LayoutLMConfig(PretrainedConfig):
    """LayoutLMConfig"""
    model_type = "layoutlm"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        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,
        position_embedding_type="absolute",
        use_cache=True,
        max_2d_position_embeddings=1024,
        **kwargs,
    ):
        """
        Initializes a LayoutLMConfig object.

        Args:
            self: The instance of the class.
            vocab_size (int, optional): The size of the vocabulary. Defaults to 30522.
            hidden_size (int, optional): The size of the hidden layers. Defaults to 768.
            num_hidden_layers (int, optional): The number of hidden layers. Defaults to 12.
            num_attention_heads (int, optional): The number of attention heads. Defaults to 12.
            intermediate_size (int, optional): The size of the intermediate layer in the transformer encoder. 
                Defaults to 3072.
            hidden_act (str, optional): The activation function for the hidden layers. Defaults to 'gelu'.
            hidden_dropout_prob (float, optional): The dropout probability for the hidden layers. Defaults to 0.1.
            attention_probs_dropout_prob (float, optional): The dropout probability for the attention probabilities. 
                Defaults to 0.1.
            max_position_embeddings (int, optional): The maximum sequence length that this model might ever be used with. 
                Defaults to 512.
            type_vocab_size (int, optional): The size of the token type vocabulary. Defaults to 2.
            initializer_range (float, optional): The standard deviation of the truncated_normal_initializer for 
                initializing all weight matrices. Defaults to 0.02.
            layer_norm_eps (float, optional): The epsilon value to use in LayerNorm layers. Defaults to 1e-12.
            pad_token_id (int, optional): The id of the padding token. Defaults to 0.
            position_embedding_type (str, optional): The type of position embedding. Defaults to 'absolute'.
            use_cache (bool, optional): Whether to use cache for the model. Defaults to True.
            max_2d_position_embeddings (int, optional): The maximum 2D sequence length that this model 
                might ever be used with. Defaults to 1024.

        Returns:
            None.

        Raises:
            None.
        """
        super().__init__(pad_token_id=pad_token_id, **kwargs)
        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.hidden_act = hidden_act
        self.intermediate_size = intermediate_size
        self.hidden_dropout_prob = hidden_dropout_prob
        self.attention_probs_dropout_prob = attention_probs_dropout_prob
        self.max_position_embeddings = max_position_embeddings
        self.type_vocab_size = type_vocab_size
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.position_embedding_type = position_embedding_type
        self.use_cache = use_cache
        self.max_2d_position_embeddings = max_2d_position_embeddings

mindnlp.transformers.models.layoutlm.configuration_layoutlm.LayoutLMConfig.__init__(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, position_embedding_type='absolute', use_cache=True, max_2d_position_embeddings=1024, **kwargs)

Initializes a LayoutLMConfig object.

PARAMETER	DESCRIPTION
self	The instance of the class.
vocab_size	The size of the vocabulary. Defaults to 30522. TYPE: int DEFAULT: 30522
hidden_size	The size of the hidden layers. Defaults to 768. TYPE: int DEFAULT: 768
num_hidden_layers	The number of hidden layers. Defaults to 12. TYPE: int DEFAULT: 12
num_attention_heads	The number of attention heads. Defaults to 12. TYPE: int DEFAULT: 12
intermediate_size	The size of the intermediate layer in the transformer encoder. Defaults to 3072. TYPE: int DEFAULT: 3072
hidden_act	The activation function for the hidden layers. Defaults to 'gelu'. TYPE: str DEFAULT: 'gelu'
hidden_dropout_prob	The dropout probability for the hidden layers. Defaults to 0.1. TYPE: float DEFAULT: 0.1
attention_probs_dropout_prob	The dropout probability for the attention probabilities. Defaults to 0.1. TYPE: float DEFAULT: 0.1
max_position_embeddings	The maximum sequence length that this model might ever be used with. Defaults to 512. TYPE: int DEFAULT: 512
type_vocab_size	The size of the token type vocabulary. Defaults to 2. TYPE: int DEFAULT: 2
initializer_range	The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Defaults to 0.02. TYPE: float DEFAULT: 0.02
layer_norm_eps	The epsilon value to use in LayerNorm layers. Defaults to 1e-12. TYPE: float DEFAULT: 1e-12
pad_token_id	The id of the padding token. Defaults to 0. TYPE: int DEFAULT: 0
position_embedding_type	The type of position embedding. Defaults to 'absolute'. TYPE: str DEFAULT: 'absolute'
use_cache	Whether to use cache for the model. Defaults to True. TYPE: bool DEFAULT: True
max_2d_position_embeddings	The maximum 2D sequence length that this model might ever be used with. Defaults to 1024. TYPE: int DEFAULT: 1024

RETURNS	DESCRIPTION
	None.

Source code in mindnlp\transformers\models\layoutlm\configuration_layoutlm.py

def __init__(
    self,
    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,
    position_embedding_type="absolute",
    use_cache=True,
    max_2d_position_embeddings=1024,
    **kwargs,
):
    """
    Initializes a LayoutLMConfig object.

    Args:
        self: The instance of the class.
        vocab_size (int, optional): The size of the vocabulary. Defaults to 30522.
        hidden_size (int, optional): The size of the hidden layers. Defaults to 768.
        num_hidden_layers (int, optional): The number of hidden layers. Defaults to 12.
        num_attention_heads (int, optional): The number of attention heads. Defaults to 12.
        intermediate_size (int, optional): The size of the intermediate layer in the transformer encoder. 
            Defaults to 3072.
        hidden_act (str, optional): The activation function for the hidden layers. Defaults to 'gelu'.
        hidden_dropout_prob (float, optional): The dropout probability for the hidden layers. Defaults to 0.1.
        attention_probs_dropout_prob (float, optional): The dropout probability for the attention probabilities. 
            Defaults to 0.1.
        max_position_embeddings (int, optional): The maximum sequence length that this model might ever be used with. 
            Defaults to 512.
        type_vocab_size (int, optional): The size of the token type vocabulary. Defaults to 2.
        initializer_range (float, optional): The standard deviation of the truncated_normal_initializer for 
            initializing all weight matrices. Defaults to 0.02.
        layer_norm_eps (float, optional): The epsilon value to use in LayerNorm layers. Defaults to 1e-12.
        pad_token_id (int, optional): The id of the padding token. Defaults to 0.
        position_embedding_type (str, optional): The type of position embedding. Defaults to 'absolute'.
        use_cache (bool, optional): Whether to use cache for the model. Defaults to True.
        max_2d_position_embeddings (int, optional): The maximum 2D sequence length that this model 
            might ever be used with. Defaults to 1024.

    Returns:
        None.

    Raises:
        None.
    """
    super().__init__(pad_token_id=pad_token_id, **kwargs)
    self.vocab_size = vocab_size
    self.hidden_size = hidden_size
    self.num_hidden_layers = num_hidden_layers
    self.num_attention_heads = num_attention_heads
    self.hidden_act = hidden_act
    self.intermediate_size = intermediate_size
    self.hidden_dropout_prob = hidden_dropout_prob
    self.attention_probs_dropout_prob = attention_probs_dropout_prob
    self.max_position_embeddings = max_position_embeddings
    self.type_vocab_size = type_vocab_size
    self.initializer_range = initializer_range
    self.layer_norm_eps = layer_norm_eps
    self.position_embedding_type = position_embedding_type
    self.use_cache = use_cache
    self.max_2d_position_embeddings = max_2d_position_embeddings