c-my/transformers
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix documention of book in LayoutLM (#9017)

Browse Source
This commit is contained in:
Sylvain Gugger
2020-12-10 09:28:49 -05:00
committed by GitHub
parent c95de29e31
commit 35bffd70e2
1 changed files with 8 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/transformers/models/layoutlm/modeling_layoutlm.py
+8 -10
View File
@@ -562,7 +562,7 @@ LAYOUTLM_START_DOCSTRING = r"""
LAYOUTLM_INPUTS_DOCSTRING = r"""
Args:
input_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`):
input_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`):
Indices of input sequence tokens in the vocabulary.
Indices can be obtained using :class:`transformers.LayoutLMTokenizer`. See
@@ -570,22 +570,20 @@ LAYOUTLM_INPUTS_DOCSTRING = r"""
details.
`What are input IDs? <../glossary.html#input-ids>`__
bbox (:obj:`torch.LongTensor` of shape :obj:`{0}`, `optional`):
bbox (:obj:`torch.LongTensor` of shape :obj:`({0}, 4)`, `optional`):
Bounding Boxes of each input sequence tokens. Selected in the range ``[0, config.max_2d_position_embeddings
- 1]``.
`What are bboxes? <../glossary.html#position-ids>`_
attention_mask (:obj:`torch.FloatTensor` of shape :obj:`{0}`, `optional`):
attention_mask (:obj:`torch.FloatTensor` of shape :obj:`({0})`, `optional`):
Mask to avoid performing attention on padding token indices. Mask values selected in ``[0, 1]``: ``1`` for
tokens that are NOT MASKED, ``0`` for MASKED tokens.
`What are attention masks? <../glossary.html#attention-mask>`__
token_type_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`, `optional`):
token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
Segment token indices to indicate first and second portions of the inputs. Indices are selected in ``[0,
1]``: ``0`` corresponds to a `sentence A` token, ``1`` corresponds to a `sentence B` token
`What are token type IDs? <../glossary.html#token-type-ids>`_
position_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`, `optional`):
position_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
Indices of positions of each input sequence tokens in the position embeddings. Selected in the range ``[0,
config.max_position_embeddings - 1]``.
@@ -643,7 +641,7 @@ class LayoutLMModel(LayoutLMPreTrainedModel):
for layer, heads in heads_to_prune.items():
self.encoder.layer[layer].attention.prune_heads(heads)
@add_start_docstrings_to_model_forward(LAYOUTLM_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
@add_start_docstrings_to_model_forward(LAYOUTLM_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="layoutlm-base-uncased",
@@ -784,7 +782,7 @@ class LayoutLMForMaskedLM(LayoutLMPreTrainedModel):
def set_output_embeddings(self, new_embeddings):
self.cls.predictions.decoder = new_embeddings
@add_start_docstrings_to_model_forward(LAYOUTLM_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
@add_start_docstrings_to_model_forward(LAYOUTLM_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="layoutlm-base-uncased",
@@ -872,7 +870,7 @@ class LayoutLMForTokenClassification(LayoutLMPreTrainedModel):
def get_input_embeddings(self):
return self.layoutlm.embeddings.word_embeddings
@add_start_docstrings_to_model_forward(LAYOUTLM_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
@add_start_docstrings_to_model_forward(LAYOUTLM_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint="layoutlm-base-uncased",