Skip to content

GitLab

Unverified Commit 91c2278b authored by amyeroberts's avatar amyeroberts Committed by GitHub
Browse files

Update modeling doc strings FE -> IP (#21106) 

* Update docs examples FE -> IP

* Remove _IMAGE_PROCESSOR_FOR_DOC
parent 5d3cb760
Hide whitespace changes
Inline Side-by-side
Showing with 32 additions and 67 deletions
src/transformers/models/altclip/modeling_altclip.py
View file @ 91c2278b
...@@ -98,7 +98,7 @@ ALTCLIP_VISION_INPUTS_DOCSTRING = r""" ...@@ -98,7 +98,7 @@ ALTCLIP_VISION_INPUTS_DOCSTRING = r"""
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail. tensors for more detail.
...@@ -133,7 +133,7 @@ ALTCLIP_INPUTS_DOCSTRING = r""" ...@@ -133,7 +133,7 @@ ALTCLIP_INPUTS_DOCSTRING = r"""
[What are position IDs?](../glossary#position-ids) [What are position IDs?](../glossary#position-ids)
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
return_loss (`bool`, *optional*): return_loss (`bool`, *optional*):
Whether or not to return the contrastive loss. Whether or not to return the contrastive loss.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
......
src/transformers/models/beit/modeling_beit.py
View file @ 91c2278b
...@@ -49,7 +49,6 @@ logger = logging.get_logger(__name__) ...@@ -49,7 +49,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "BeitConfig" _CONFIG_FOR_DOC = "BeitConfig"
_FEAT_EXTRACTOR_FOR_DOC = "BeitImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "microsoft/beit-base-patch16-224-pt22k" _CHECKPOINT_FOR_DOC = "microsoft/beit-base-patch16-224-pt22k"
...@@ -646,7 +645,6 @@ class BeitModel(BeitPreTrainedModel): ...@@ -646,7 +645,6 @@ class BeitModel(BeitPreTrainedModel):
@add_start_docstrings_to_model_forward(BEIT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(BEIT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BeitModelOutputWithPooling, output_type=BeitModelOutputWithPooling,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
...@@ -844,7 +842,6 @@ class BeitForImageClassification(BeitPreTrainedModel): ...@@ -844,7 +842,6 @@ class BeitForImageClassification(BeitPreTrainedModel):
@add_start_docstrings_to_model_forward(BEIT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(BEIT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_IMAGE_CLASS_CHECKPOINT, checkpoint=_IMAGE_CLASS_CHECKPOINT,
output_type=ImageClassifierOutput, output_type=ImageClassifierOutput,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/bit/modeling_bit.py
View file @ 91c2278b
...@@ -46,7 +46,6 @@ logger = logging.get_logger(__name__) ...@@ -46,7 +46,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "BitConfig" _CONFIG_FOR_DOC = "BitConfig"
_FEAT_EXTRACTOR_FOR_DOC = "AutoFeatureExtractor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "google/bit-50" _CHECKPOINT_FOR_DOC = "google/bit-50"
...@@ -688,8 +687,8 @@ BIT_START_DOCSTRING = r""" ...@@ -688,8 +687,8 @@ BIT_START_DOCSTRING = r"""
BIT_INPUTS_DOCSTRING = r""" BIT_INPUTS_DOCSTRING = r"""
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Pixel values can be obtained using [`AutoFeatureExtractor`]. See Pixel values. Pixel values can be obtained using [`AutoImageProcessor`]. See
[`AutoFeatureExtractor.__call__`] for details. [`AutoImageProcessor.__call__`] for details.
output_hidden_states (`bool`, *optional*): output_hidden_states (`bool`, *optional*):
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
...@@ -723,7 +722,6 @@ class BitModel(BitPreTrainedModel): ...@@ -723,7 +722,6 @@ class BitModel(BitPreTrainedModel):
@add_start_docstrings_to_model_forward(BIT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(BIT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BaseModelOutputWithPoolingAndNoAttention, output_type=BaseModelOutputWithPoolingAndNoAttention,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
...@@ -782,7 +780,6 @@ class BitForImageClassification(BitPreTrainedModel): ...@@ -782,7 +780,6 @@ class BitForImageClassification(BitPreTrainedModel):
@add_start_docstrings_to_model_forward(BIT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(BIT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_IMAGE_CLASS_CHECKPOINT, checkpoint=_IMAGE_CLASS_CHECKPOINT,
output_type=ImageClassifierOutputWithNoAttention, output_type=ImageClassifierOutputWithNoAttention,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/chinese_clip/modeling_chinese_clip.py
View file @ 91c2278b
...@@ -810,7 +810,7 @@ CHINESE_CLIP_VISION_INPUTS_DOCSTRING = r""" ...@@ -810,7 +810,7 @@ CHINESE_CLIP_VISION_INPUTS_DOCSTRING = r"""
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`ChineseCLIPFeatureExtractor`]. See [`ChineseCLIPFeatureExtractor.__call__`] for details. [`ChineseCLIPImageProcessor`]. See [`ChineseCLIPImageProcessor.__call__`] for details.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail. tensors for more detail.
...@@ -853,7 +853,7 @@ CHINESE_CLIP_INPUTS_DOCSTRING = r""" ...@@ -853,7 +853,7 @@ CHINESE_CLIP_INPUTS_DOCSTRING = r"""
[What are position IDs?](../glossary#position-ids) [What are position IDs?](../glossary#position-ids)
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`ChineseCLIPFeatureExtractor`]. See [`ChineseCLIPFeatureExtractor.__call__`] for details. [`ChineseCLIPImageProcessor`]. See [`ChineseCLIPImageProcessor.__call__`] for details.
return_loss (`bool`, *optional*): return_loss (`bool`, *optional*):
Whether or not to return the contrastive loss. Whether or not to return the contrastive loss.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
......
src/transformers/models/clip/modeling_clip.py
View file @ 91c2278b
...@@ -521,7 +521,7 @@ CLIP_VISION_INPUTS_DOCSTRING = r""" ...@@ -521,7 +521,7 @@ CLIP_VISION_INPUTS_DOCSTRING = r"""
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail. tensors for more detail.
...@@ -556,7 +556,7 @@ CLIP_INPUTS_DOCSTRING = r""" ...@@ -556,7 +556,7 @@ CLIP_INPUTS_DOCSTRING = r"""
[What are position IDs?](../glossary#position-ids) [What are position IDs?](../glossary#position-ids)
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
return_loss (`bool`, *optional*): return_loss (`bool`, *optional*):
Whether or not to return the contrastive loss. Whether or not to return the contrastive loss.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
......
src/transformers/models/clip/modeling_flax_clip.py
View file @ 91c2278b
...@@ -108,7 +108,7 @@ CLIP_VISION_INPUTS_DOCSTRING = r""" ...@@ -108,7 +108,7 @@ CLIP_VISION_INPUTS_DOCSTRING = r"""
Args: Args:
pixel_values (`numpy.ndarray` of shape `(batch_size, num_channels, height, width)`): pixel_values (`numpy.ndarray` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail. tensors for more detail.
...@@ -143,7 +143,7 @@ CLIP_INPUTS_DOCSTRING = r""" ...@@ -143,7 +143,7 @@ CLIP_INPUTS_DOCSTRING = r"""
[What are position IDs?](../glossary#position-ids) [What are position IDs?](../glossary#position-ids)
pixel_values (`numpy.ndarray` of shape `(batch_size, num_channels, height, width)`): pixel_values (`numpy.ndarray` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail. tensors for more detail.
...@@ -893,7 +893,7 @@ class FlaxCLIPPreTrainedModel(FlaxPreTrainedModel): ...@@ -893,7 +893,7 @@ class FlaxCLIPPreTrainedModel(FlaxPreTrainedModel):
Args: Args:
pixel_values (`numpy.ndarray` of shape `(batch_size, num_channels, height, width)`): pixel_values (`numpy.ndarray` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained
using [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. using [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
Returns: Returns:
image_features (`jnp.ndarray` of shape `(batch_size, output_dim`): The image embeddings obtained by image_features (`jnp.ndarray` of shape `(batch_size, output_dim`): The image embeddings obtained by
......
src/transformers/models/clip/modeling_tf_clip.py
View file @ 91c2278b
...@@ -993,8 +993,8 @@ CLIP_TEXT_INPUTS_DOCSTRING = r""" ...@@ -993,8 +993,8 @@ CLIP_TEXT_INPUTS_DOCSTRING = r"""
CLIP_VISION_INPUTS_DOCSTRING = r""" CLIP_VISION_INPUTS_DOCSTRING = r"""
Args: Args:
pixel_values (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` ``Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `(batch_size, num_channels, height, width)`): pixel_values (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` ``Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `(batch_size, num_channels, height, width)`):
Pixel values. Pixel values can be obtained using [`CLIPFeatureExtractor`]. See Pixel values. Pixel values can be obtained using [`CLIPImageProcessor`]. See
[`CLIPFeatureExtractor.__call__`] for details. output_attentions (`bool`, *optional*): Whether or not to [`CLIPImageProcessor.__call__`] for details. output_attentions (`bool`, *optional*): Whether or not to
return the attentions tensors of all attention layers. See `attentions` under returned tensors for more return the attentions tensors of all attention layers. See `attentions` under returned tensors for more
detail. This argument can be used only in eager mode, in graph mode the value in the config will be used detail. This argument can be used only in eager mode, in graph mode the value in the config will be used
instead. instead.
...@@ -1020,8 +1020,8 @@ CLIP_INPUTS_DOCSTRING = r""" ...@@ -1020,8 +1020,8 @@ CLIP_INPUTS_DOCSTRING = r"""
[What are input IDs?](../glossary#input-ids) [What are input IDs?](../glossary#input-ids)
pixel_values (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` `Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `(batch_size, num_channels, height, width)`): pixel_values (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` `Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `(batch_size, num_channels, height, width)`):
Pixel values. Pixel values can be obtained using [`CLIPFeatureExtractor`]. See Pixel values. Pixel values can be obtained using [`CLIPImageProcessor`]. See
[`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor.__call__`] for details.
attention_mask (`np.ndarray` or `tf.Tensor` of shape `({0})`, *optional*): attention_mask (`np.ndarray` or `tf.Tensor` of shape `({0})`, *optional*):
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
......
src/transformers/models/clipseg/modeling_clipseg.py
View file @ 91c2278b
...@@ -530,7 +530,7 @@ CLIPSEG_VISION_INPUTS_DOCSTRING = r""" ...@@ -530,7 +530,7 @@ CLIPSEG_VISION_INPUTS_DOCSTRING = r"""
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail. tensors for more detail.
...@@ -565,7 +565,7 @@ CLIPSEG_INPUTS_DOCSTRING = r""" ...@@ -565,7 +565,7 @@ CLIPSEG_INPUTS_DOCSTRING = r"""
[What are position IDs?](../glossary#position-ids) [What are position IDs?](../glossary#position-ids)
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
return_loss (`bool`, *optional*): return_loss (`bool`, *optional*):
Whether or not to return the contrastive loss. Whether or not to return the contrastive loss.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
......
src/transformers/models/convnext/modeling_convnext.py
View file @ 91c2278b
...@@ -44,7 +44,6 @@ logger = logging.get_logger(__name__) ...@@ -44,7 +44,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "ConvNextConfig" _CONFIG_FOR_DOC = "ConvNextConfig"
_FEAT_EXTRACTOR_FOR_DOC = "ConvNextImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "facebook/convnext-tiny-224" _CHECKPOINT_FOR_DOC = "facebook/convnext-tiny-224"
...@@ -346,7 +345,6 @@ class ConvNextModel(ConvNextPreTrainedModel): ...@@ -346,7 +345,6 @@ class ConvNextModel(ConvNextPreTrainedModel):
@add_start_docstrings_to_model_forward(CONVNEXT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(CONVNEXT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BaseModelOutputWithPoolingAndNoAttention, output_type=BaseModelOutputWithPoolingAndNoAttention,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
...@@ -414,7 +412,6 @@ class ConvNextForImageClassification(ConvNextPreTrainedModel): ...@@ -414,7 +412,6 @@ class ConvNextForImageClassification(ConvNextPreTrainedModel):
@add_start_docstrings_to_model_forward(CONVNEXT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(CONVNEXT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_IMAGE_CLASS_CHECKPOINT, checkpoint=_IMAGE_CLASS_CHECKPOINT,
output_type=ImageClassifierOutputWithNoAttention, output_type=ImageClassifierOutputWithNoAttention,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/cvt/modeling_cvt.py
View file @ 91c2278b
...@@ -35,7 +35,6 @@ logger = logging.get_logger(__name__) ...@@ -35,7 +35,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "CvtConfig" _CONFIG_FOR_DOC = "CvtConfig"
_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "microsoft/cvt-13" _CHECKPOINT_FOR_DOC = "microsoft/cvt-13"
...@@ -605,7 +604,6 @@ class CvtModel(CvtPreTrainedModel): ...@@ -605,7 +604,6 @@ class CvtModel(CvtPreTrainedModel):
@add_start_docstrings_to_model_forward(CVT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(CVT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BaseModelOutputWithCLSToken, output_type=BaseModelOutputWithCLSToken,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
...@@ -668,7 +666,6 @@ class CvtForImageClassification(CvtPreTrainedModel): ...@@ -668,7 +666,6 @@ class CvtForImageClassification(CvtPreTrainedModel):
@add_start_docstrings_to_model_forward(CVT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(CVT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_IMAGE_CLASS_CHECKPOINT, checkpoint=_IMAGE_CLASS_CHECKPOINT,
output_type=ImageClassifierOutputWithNoAttention, output_type=ImageClassifierOutputWithNoAttention,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/data2vec/modeling_data2vec_vision.py
View file @ 91c2278b
...@@ -48,7 +48,6 @@ logger = logging.get_logger(__name__) ...@@ -48,7 +48,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "Data2VecVisionConfig" _CONFIG_FOR_DOC = "Data2VecVisionConfig"
_FEAT_EXTRACTOR_FOR_DOC = "BeitImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "facebook/data2vec-vision-base" _CHECKPOINT_FOR_DOC = "facebook/data2vec-vision-base"
...@@ -660,7 +659,6 @@ class Data2VecVisionModel(Data2VecVisionPreTrainedModel): ...@@ -660,7 +659,6 @@ class Data2VecVisionModel(Data2VecVisionPreTrainedModel):
@add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=Data2VecVisionModelOutputWithPooling, output_type=Data2VecVisionModelOutputWithPooling,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
...@@ -760,7 +758,6 @@ class Data2VecVisionForImageClassification(Data2VecVisionPreTrainedModel): ...@@ -760,7 +758,6 @@ class Data2VecVisionForImageClassification(Data2VecVisionPreTrainedModel):
@add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_IMAGE_CLASS_CHECKPOINT, checkpoint=_IMAGE_CLASS_CHECKPOINT,
output_type=ImageClassifierOutput, output_type=ImageClassifierOutput,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/data2vec/modeling_tf_data2vec_vision.py
View file @ 91c2278b
...@@ -53,7 +53,6 @@ logger = logging.get_logger(__name__) ...@@ -53,7 +53,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "Data2VecVisionConfig" _CONFIG_FOR_DOC = "Data2VecVisionConfig"
_FEAT_EXTRACTOR_FOR_DOC = "BeitImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "facebook/data2vec-vision-base" _CHECKPOINT_FOR_DOC = "facebook/data2vec-vision-base"
...@@ -894,7 +893,6 @@ class TFData2VecVisionModel(TFData2VecVisionPreTrainedModel): ...@@ -894,7 +893,6 @@ class TFData2VecVisionModel(TFData2VecVisionPreTrainedModel):
@unpack_inputs @unpack_inputs
@add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TFData2VecVisionModelOutputWithPooling, output_type=TFData2VecVisionModelOutputWithPooling,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
...@@ -960,7 +958,6 @@ class TFData2VecVisionForImageClassification(TFData2VecVisionPreTrainedModel, TF ...@@ -960,7 +958,6 @@ class TFData2VecVisionForImageClassification(TFData2VecVisionPreTrainedModel, TF
@unpack_inputs @unpack_inputs
@add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_IMAGE_CLASS_CHECKPOINT, checkpoint=_IMAGE_CLASS_CHECKPOINT,
output_type=TFSequenceClassifierOutput, output_type=TFSequenceClassifierOutput,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/deit/modeling_deit.py
View file @ 91c2278b
...@@ -44,7 +44,6 @@ logger = logging.get_logger(__name__) ...@@ -44,7 +44,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "DeiTConfig" _CONFIG_FOR_DOC = "DeiTConfig"
_FEAT_EXTRACTOR_FOR_DOC = "DeiTImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "facebook/deit-base-distilled-patch16-224" _CHECKPOINT_FOR_DOC = "facebook/deit-base-distilled-patch16-224"
...@@ -483,7 +482,6 @@ class DeiTModel(DeiTPreTrainedModel): ...@@ -483,7 +482,6 @@ class DeiTModel(DeiTPreTrainedModel):
@add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BaseModelOutputWithPooling, output_type=BaseModelOutputWithPooling,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
...@@ -854,7 +852,6 @@ class DeiTForImageClassificationWithTeacher(DeiTPreTrainedModel): ...@@ -854,7 +852,6 @@ class DeiTForImageClassificationWithTeacher(DeiTPreTrainedModel):
@add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_IMAGE_CLASS_CHECKPOINT, checkpoint=_IMAGE_CLASS_CHECKPOINT,
output_type=DeiTForImageClassificationWithTeacherOutput, output_type=DeiTForImageClassificationWithTeacherOutput,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/deit/modeling_tf_deit.py
View file @ 91c2278b
...@@ -52,7 +52,6 @@ logger = logging.get_logger(__name__) ...@@ -52,7 +52,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "DeiTConfig" _CONFIG_FOR_DOC = "DeiTConfig"
_FEAT_EXTRACTOR_FOR_DOC = "DeiTImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "facebook/deit-base-distilled-patch16-224" _CHECKPOINT_FOR_DOC = "facebook/deit-base-distilled-patch16-224"
...@@ -651,7 +650,6 @@ class TFDeiTModel(TFDeiTPreTrainedModel): ...@@ -651,7 +650,6 @@ class TFDeiTModel(TFDeiTPreTrainedModel):
@unpack_inputs @unpack_inputs
@add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TFBaseModelOutputWithPooling, output_type=TFBaseModelOutputWithPooling,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
...@@ -1009,7 +1007,6 @@ class TFDeiTForImageClassificationWithTeacher(TFDeiTPreTrainedModel): ...@@ -1009,7 +1007,6 @@ class TFDeiTForImageClassificationWithTeacher(TFDeiTPreTrainedModel):
@unpack_inputs @unpack_inputs
@add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_IMAGE_CLASS_CHECKPOINT, checkpoint=_IMAGE_CLASS_CHECKPOINT,
output_type=TFDeiTForImageClassificationWithTeacherOutput, output_type=TFDeiTForImageClassificationWithTeacherOutput,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/dinat/modeling_dinat.py
View file @ 91c2278b
...@@ -57,7 +57,6 @@ logger = logging.get_logger(__name__) ...@@ -57,7 +57,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "DinatConfig" _CONFIG_FOR_DOC = "DinatConfig"
_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "shi-labs/dinat-mini-in1k-224" _CHECKPOINT_FOR_DOC = "shi-labs/dinat-mini-in1k-224"
...@@ -730,7 +729,6 @@ class DinatModel(DinatPreTrainedModel): ...@@ -730,7 +729,6 @@ class DinatModel(DinatPreTrainedModel):
@add_start_docstrings_to_model_forward(DINAT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DINAT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=DinatModelOutput, output_type=DinatModelOutput,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
...@@ -810,7 +808,6 @@ class DinatForImageClassification(DinatPreTrainedModel): ...@@ -810,7 +808,6 @@ class DinatForImageClassification(DinatPreTrainedModel):
@add_start_docstrings_to_model_forward(DINAT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DINAT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_IMAGE_CLASS_CHECKPOINT, checkpoint=_IMAGE_CLASS_CHECKPOINT,
output_type=DinatImageClassifierOutput, output_type=DinatImageClassifierOutput,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/donut/modeling_donut_swin.py
View file @ 91c2278b
...@@ -43,7 +43,6 @@ logger = logging.get_logger(__name__) ...@@ -43,7 +43,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "DonutSwinConfig" _CONFIG_FOR_DOC = "DonutSwinConfig"
_FEAT_EXTRACTOR_FOR_DOC = "AutoFeatureExtractor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "https://huggingface.co/naver-clova-ix/donut-base" _CHECKPOINT_FOR_DOC = "https://huggingface.co/naver-clova-ix/donut-base"
...@@ -847,8 +846,8 @@ SWIN_START_DOCSTRING = r""" ...@@ -847,8 +846,8 @@ SWIN_START_DOCSTRING = r"""
SWIN_INPUTS_DOCSTRING = r""" SWIN_INPUTS_DOCSTRING = r"""
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Pixel values can be obtained using [`AutoFeatureExtractor`]. See Pixel values. Pixel values can be obtained using [`AutoImageProcessor`]. See
[`AutoFeatureExtractor.__call__`] for details. [`AutoImageProcessor.__call__`] for details.
head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*): head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`: Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
...@@ -898,7 +897,6 @@ class DonutSwinModel(DonutSwinPreTrainedModel): ...@@ -898,7 +897,6 @@ class DonutSwinModel(DonutSwinPreTrainedModel):
@add_start_docstrings_to_model_forward(SWIN_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(SWIN_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=DonutSwinModelOutput, output_type=DonutSwinModelOutput,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/dpt/modeling_dpt.py
View file @ 91c2278b
...@@ -49,7 +49,6 @@ logger = logging.get_logger(__name__) ...@@ -49,7 +49,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "DPTConfig" _CONFIG_FOR_DOC = "DPTConfig"
_FEAT_EXTRACTOR_FOR_DOC = "DPTImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "Intel/dpt-large" _CHECKPOINT_FOR_DOC = "Intel/dpt-large"
...@@ -898,7 +897,6 @@ class DPTModel(DPTPreTrainedModel): ...@@ -898,7 +897,6 @@ class DPTModel(DPTPreTrainedModel):
@add_start_docstrings_to_model_forward(DPT_INPUTS_DOCSTRING) @add_start_docstrings_to_model_forward(DPT_INPUTS_DOCSTRING)
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BaseModelOutputWithPoolingAndIntermediateActivations, output_type=BaseModelOutputWithPoolingAndIntermediateActivations,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
src/transformers/models/flava/modeling_flava.py
View file @ 91c2278b
...@@ -51,7 +51,6 @@ _CHECKPOINT_FOR_DOC = "facebook/flava-full" ...@@ -51,7 +51,6 @@ _CHECKPOINT_FOR_DOC = "facebook/flava-full"
# Codebook docstring # Codebook docstring
_CHECKPOINT_FOR_CODEBOOK_DOC = "facebook/flava-image-codebook" _CHECKPOINT_FOR_CODEBOOK_DOC = "facebook/flava-image-codebook"
_FEAT_EXTRACTOR_FOR_DOC = "FlavaFeatureExtractor"
_CONFIG_CLASS_FOR_IMAGE_MODEL_DOC = "FlavaImageConfig" _CONFIG_CLASS_FOR_IMAGE_MODEL_DOC = "FlavaImageConfig"
_CONFIG_CLASS_FOR_TEXT_MODEL_DOC = "FlavaTextConfig" _CONFIG_CLASS_FOR_TEXT_MODEL_DOC = "FlavaTextConfig"
_CONFIG_CLASS_FOR_MULTIMODAL_MODEL_DOC = "FlavaMultimodalConfig" _CONFIG_CLASS_FOR_MULTIMODAL_MODEL_DOC = "FlavaMultimodalConfig"
...@@ -750,8 +749,8 @@ FLAVA_INPUTS_DOCSTRING_COMMON = r""" ...@@ -750,8 +749,8 @@ FLAVA_INPUTS_DOCSTRING_COMMON = r"""
FLAVA_IMAGE_INPUTS_DOCSTRING_BASE = r""" FLAVA_IMAGE_INPUTS_DOCSTRING_BASE = r"""
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Pixel values can be obtained using [`FlavaFeatureExtractor`]. See Pixel values. Pixel values can be obtained using [`FlavaImageProcessor`]. See
[`FlavaFeatureExtractor.__call__`] for details. [`FlavaImageProcessor.__call__`] for details.
bool_masked_pos (`torch.BoolTensor` of shape `(batch_size, image_num_patches)`): bool_masked_pos (`torch.BoolTensor` of shape `(batch_size, image_num_patches)`):
Boolean masked positions. Indicates which patches are masked (1) and which aren't (0). Boolean masked positions. Indicates which patches are masked (1) and which aren't (0).
...@@ -926,7 +925,6 @@ class FlavaImageModel(FlavaPreTrainedModel): ...@@ -926,7 +925,6 @@ class FlavaImageModel(FlavaPreTrainedModel):
@add_start_docstrings_to_model_forward(FLAVA_IMAGE_INPUTS_DOCSTRING.format("batch_size, image_num_patches")) @add_start_docstrings_to_model_forward(FLAVA_IMAGE_INPUTS_DOCSTRING.format("batch_size, image_num_patches"))
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BaseModelOutputWithPooling, output_type=BaseModelOutputWithPooling,
config_class=_CONFIG_CLASS_FOR_IMAGE_MODEL_DOC, config_class=_CONFIG_CLASS_FOR_IMAGE_MODEL_DOC,
...@@ -1568,22 +1566,22 @@ class FlavaImageCodebook(FlavaPreTrainedModel): ...@@ -1568,22 +1566,22 @@ class FlavaImageCodebook(FlavaPreTrainedModel):
""" """
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Codebook pixel values can be obtained using [`FlavaFeatureExtractor`] by passing Pixel values. Codebook pixel values can be obtained using [`FlavaImageProcessor`] by passing
`return_codebook_pixels=True`. See [`FlavaFeatureExtractor.__call__`] for details. `return_codebook_pixels=True`. See [`FlavaImageProcessor.__call__`] for details.
Examples: Examples:
```python ```python
>>> from PIL import Image >>> from PIL import Image
>>> import requests >>> import requests
>>> from transformers import FlavaFeatureExtractor, FlavaImageCodebook >>> from transformers import FlavaImageProcessor, FlavaImageCodebook
>>> model = FlavaImageCodebook.from_pretrained("{0}") >>> model = FlavaImageCodebook.from_pretrained("{0}")
>>> feature_extractor = FlavaFeatureExtractor.from_pretrained("{0}") >>> image_processor = FlavaImageProcessor.from_pretrained("{0}")
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw) >>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = feature_extractor([image], return_codebook_pixels=True, return_tensors="pt") >>> inputs = image_processor([image], return_codebook_pixels=True, return_tensors="pt")
>>> inputs = dict(pixel_values=inputs.codebook_pixel_values) >>> inputs = dict(pixel_values=inputs.codebook_pixel_values)
>>> outputs = model.get_codebook_indices(**inputs) >>> outputs = model.get_codebook_indices(**inputs)
...@@ -1602,23 +1600,23 @@ class FlavaImageCodebook(FlavaPreTrainedModel): ...@@ -1602,23 +1600,23 @@ class FlavaImageCodebook(FlavaPreTrainedModel):
""" """
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Codebook pixel values can be obtained using [`FlavaFeatureExtractor`] by passing Pixel values. Codebook pixel values can be obtained using [`FlavaImageProcessor`] by passing
`return_codebook_pixels=True`. See [`FlavaFeatureExtractor.__call__`] for details. `return_codebook_pixels=True`. See [`FlavaImageProcessor.__call__`] for details.
Examples: Examples:
```python ```python
>>> from PIL import Image >>> from PIL import Image
>>> import requests >>> import requests
>>> from transformers import FlavaFeatureExtractor, FlavaImageCodebook >>> from transformers import FlavaImageProcessor, FlavaImageCodebook
>>> model = FlavaImageCodebook.from_pretrained("{0}") >>> model = FlavaImageCodebook.from_pretrained("{0}")
>>> feature_extractor = FlavaFeatureExtractor.from_pretrained("{0}") >>> image_processor = FlavaImageProcessor.from_pretrained("{0}")
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw) >>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = feature_extractor([image], return_codebook_pixels=True, return_tensors="pt") >>> inputs = image_processor([image], return_codebook_pixels=True, return_tensors="pt")
>>> inputs = dict(pixel_values=inputs.codebook_pixel_values) >>> inputs = dict(pixel_values=inputs.codebook_pixel_values)
>>> outputs = model(**inputs) >>> outputs = model(**inputs)
......
src/transformers/models/git/modeling_git.py
View file @ 91c2278b
...@@ -916,7 +916,7 @@ GIT_VISION_INPUTS_DOCSTRING = r""" ...@@ -916,7 +916,7 @@ GIT_VISION_INPUTS_DOCSTRING = r"""
Args: Args:
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
[`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details. [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
output_attentions (`bool`, *optional*): output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail. tensors for more detail.
......
src/transformers/models/glpn/modeling_glpn.py
View file @ 91c2278b
...@@ -41,7 +41,6 @@ logger = logging.get_logger(__name__) ...@@ -41,7 +41,6 @@ logger = logging.get_logger(__name__)
# General docstring # General docstring
_CONFIG_FOR_DOC = "GLPNConfig" _CONFIG_FOR_DOC = "GLPNConfig"
_FEAT_EXTRACTOR_FOR_DOC = "GLPNImageProcessor"
# Base docstring # Base docstring
_CHECKPOINT_FOR_DOC = "vinvino02/glpn-kitti" _CHECKPOINT_FOR_DOC = "vinvino02/glpn-kitti"
...@@ -503,7 +502,6 @@ class GLPNModel(GLPNPreTrainedModel): ...@@ -503,7 +502,6 @@ class GLPNModel(GLPNPreTrainedModel):
@add_start_docstrings_to_model_forward(GLPN_INPUTS_DOCSTRING.format("(batch_size, sequence_length)")) @add_start_docstrings_to_model_forward(GLPN_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
@add_code_sample_docstrings( @add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC, checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BaseModelOutput, output_type=BaseModelOutput,
config_class=_CONFIG_FOR_DOC, config_class=_CONFIG_FOR_DOC,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment