FLAVA
Overview
The FLAVA model was proposed in FLAVA: A Foundational Language And Vision Alignment Model by Amanpreet Singh, Ronghang Hu, Vedanuj Goswami, Guillaume Couairon, Wojciech Galuba, Marcus Rohrbach, and Douwe Kiela and is accepted at CVPR 2022.
The paper aims at creating a single unified foundation model which can work across vision, language as well as vision-and-language multimodal tasks.
The abstract from the paper is the following:
State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a βfoundationβ, that targets all modalities at once β a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision and language tasks. We introduce FLAVA as such a model and demonstrate impressive performance on a wide range of 35 tasks spanning these target modalities.
This model was contributed by aps. The original code can be found here.
FlavaConfig
class transformers.FlavaConfig
< source >( image_config: typing.Dict[str, typing.Any] = None text_config: typing.Dict[str, typing.Any] = None multimodal_config: typing.Dict[str, typing.Any] = None image_codebook_config: typing.Dict[str, typing.Any] = None hidden_size: int = 768 layer_norm_eps: float = 1e-12 projection_dim: int = 768 init_codebook: bool = True logit_scale_init_value: float = 2.6592 initializer_range: float = 0.02 ce_ignore_index: int = -100 mim_weight: float = 1.0 mlm_weight: float = 1.0 global_contrastive_weight: float = 1.0 itm_weight: float = 1.0 mmm_image_weight: float = 1.0 mmm_text_weight: float = 1.0 global_backprop_contrastive: bool = True skip_unmasked_multimodal_encoder: bool = True return_loss: bool = True **kwargs )
Parameters
-
text_config (
dict
, optional) — Dictionary of configuration options used to initialize FlavaTextConfig. -
image_config (
dict
, optional) — Dictionary of configuration options used to initialize FlavaImageConfig. -
multimodal_config (
dict
, optional) — Dictionary of configuration options used to initialize FlavaMultimodalConfig. - hidden_size (
int
, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer. -
layer_norm_eps (
float
, optional, defaults to 1e-12) — The epsilon used by the layer normalization layers. -
projection_dim (
int
, optional, defaults to 512) — Dimentionality of text and image projection layers. -
logit_scale_init_value (
float
, optional, defaults to 2.6592) — The inital value of the logit_scale paramter. Default is used as per the original FLAVA/CLIP implementation. -
initializer_range (
float
, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. -
ce_ignore_index (
int
, optional, defaults to -100) — Cross entropy index to ignore. -
mim_weight (
float
, optional, defaults to 1.0) — Weight to be assigned to MIM (Masked Image Modeling) unimodal loss -
mlm_weight (
float
, optional, defaults to 1.0) — Weight to be assigned to MLM (Masked Language Modeling) unimodal loss -
global_contrastive_weight (
float
, optional, defaults to 1.0) — Weight to be assigned to global contrastive cross-alignment loss. -
itm_weight (
float
, optional, defaults to 1.0) — Weight to be assigned to image-text matching multimodal loss. -
mmm_image_weight (
float
, optional, defaults to 1.0) — Weight to be assigned to MMM loss’s image part. -
mmm_text_weight (
float
, optional, defaults to 1.0) — Weight to be assigned to MMM loss’s text part. -
global_backprop_contrastive (
bool
, optional, defaults toTrue
) — Whether to use global backpropgation through all workers in contrastive loss. -
skip_unmasked_multimodal_encoder (
bool
, optional, defaults toTrue
) — Whether to skip running unmasked multimodal encoder whose outputs are not used by FLAVA losses. -
return_loss (
bool
, optional, defaults toTrue
) — Whether to return loss or not - kwargs (optional) — Dictionary of keyword arguments.
FlavaConfig is the configuration class to store the configuration of a FlavaModel. It is used to instantiate FLAVA model according to the specified arguments, defining the text model, image model, image codebook and multimodal model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the FLAVA facebook/flava-full architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
>>> from transformers import FlavaConfig, FlavaModel, FlavaForPreTraining
>>> # Initializing a FlavaConfig with style configuration
>>> configuration = FlavaConfig()
>>> # Initializing a FlavaModel and FlavaForPreTraining model (with random weights) from the style configuration
>>> model = FlavaModel(configuration)
>>> model_pre = FlavaForPreTraining(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
>>> configuration_pre = model_pre.config
from_configs
< source >( image_config: FlavaImageConfig text_config: FlavaTextConfig multimodal_config: FlavaMultimodalConfig image_codebook_config: FlavaImageCodebookConfig **kwargs ) β FlavaConfig
Instantiate a FlavaConfig (or a derived class) from flava text model configuration, flava image model configuration, flava multimodal model and flava codebook model configuration.
to_dict
< source >(
)
β
Dict[str, any]
Returns
Dict[str, any]
Dictionary of all the attributes that make up this configuration instance,
Serializes this instance to a Python dictionary. Override the default to_dict().
FlavaTextConfig
class transformers.FlavaTextConfig
< source >( vocab_size: int = 30522 type_vocab_size: int = 2 max_position_embeddings: int = 512 position_embedding_type: str = 'absolute' hidden_size: int = 768 num_hidden_layers: int = 12 num_attention_heads: int = 12 intermediate_size: int = 3072 hidden_act: str = 'gelu' hidden_dropout_prob: float = 0.0 attention_probs_dropout_prob: float = 0.0 initializer_range: float = 0.02 layer_norm_eps: float = 1e-12 pad_token_id: int = 0 qkv_bias: bool = True **kwargs )
Parameters
-
vocab_size (
int
, optional, defaults to 30522) — Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by theinputs_ids
passed when calling FlavaTextModel. -
type_vocab_size (
int
, optional, defaults to 2) — The vocabulary size of thetoken_type_ids
passed when calling FlavaTextModel. Note that even though text encoder allowstoken_type_ids
’s value as 2, for text-only pretraining and fine-tuning, only 1 is used similar to RoBERTa. -
max_position_embeddings (
int
, optional, defaults to 512) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). For VL, max_length passed to model is 77. -
position_embedding_type (
str
, optional, defaults to"absolute"
) — Type of position embedding. Choose one of"absolute"
,"relative_key"
,"relative_key_query"
. For positional embeddings use"absolute"
. For more information on"relative_key"
, please refer to Self-Attention with Relative Position Representations (Shaw et al.). For more information on"relative_key_query"
, please refer to Method 4 in Improve Transformer Models with Better Relative Position Embeddings (Huang et al.). - hidden_size (
int
, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer. - num_hidden_layers (
int
, optional, defaults to 12) — Number of hidden layers in the Transformer encoder. -
num_attention_heads (
int
, optional, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder. -
intermediate_size (
int
, optional, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder. - hidden_act (
str
orfunction
, optional, defaults to"gelu"
) — The non-linear activation function (function or string) in the encoder and pooler. If string,"gelu"
,"relu"
,"selu"
and"gelu_new"
are supported. - hidden_dropout_prob (
float
, optional, defaults to 0.1) — The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. -
attention_probs_dropout_prob (
float
, optional, defaults to 0.1) — The dropout ratio for the attention probabilities. -
initializer_range (
float
, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. -
layer_norm_eps (
float
, optional, defaults to 1e-12) — The epsilon used by the layer normalization layers. -
image_size (
int
, optional, defaults to 224) — The size (resolution) of each image. -
patch_size (
int
, optional, defaults to 16) — The size (resolution) of each patch. -
num_channels (
int
, optional, defaults to 3) — The number of input channels. -
qkv_bias (
bool
, optional, defaults toTrue
) — Whether to add a bias to the queries, keys and values.
This is the configuration class to store the configuration of a FlavaTextModel. It is used to instantiate an FLAVA model according to the specified arguments, defining the model architecture.
Instantiating a configuration with the defaults will yield a similar configuration to that of the FLAVA facebook/flava-full architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
>>> from transformers import FlavaTextConfig, FlavaTextModel
>>> # Initializing a FlavaTextModel with style configuration
>>> configuration = FlavaTextConfig()
>>> # Initializing a FlavaTextModel model (with random weights) from the style configuration
>>> model = FlavaTextModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
FlavaImageConfig
class transformers.FlavaImageConfig
< source >( hidden_size: int = 768 num_hidden_layers: int = 12 num_attention_heads: int = 12 intermediate_size: int = 3072 hidden_act: int = 'gelu' hidden_dropout_prob: float = 0.0 attention_probs_dropout_prob: float = 0.0 initializer_range: float = 0.02 layer_norm_eps: float = 1e-12 image_size: int = 224 patch_size: int = 16 num_channels: int = 3 qkv_bias: bool = True mask_token: bool = True vocab_size: int = 8192 **kwargs )
Parameters
- hidden_size (
int
, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer. - num_hidden_layers (
int
, optional, defaults to 12) — Number of hidden layers in the Transformer encoder. -
num_attention_heads (
int
, optional, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder. -
intermediate_size (
int
, optional, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder. - hidden_act (
str
orfunction
, optional, defaults to"gelu"
) — The non-linear activation function (function or string) in the encoder and pooler. If string,"gelu"
,"relu"
,"selu"
and"gelu_new"
are supported. - hidden_dropout_prob (
float
, optional, defaults to 0.1) — The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. -
attention_probs_dropout_prob (
float
, optional, defaults to 0.1) — The dropout ratio for the attention probabilities. -
initializer_range (
float
, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. -
layer_norm_eps (
float
, optional, defaults to 1e-12) — The epsilon used by the layer normalization layers. -
image_size (
int
, optional, defaults to 224) — The size (resolution) of each image. -
patch_size (
int
, optional, defaults to 16) — The size (resolution) of each patch. -
num_channels (
int
, optional, defaults to 3) — The number of input channels. -
qkv_bias (
bool
, optional, defaults toTrue
) — Whether to add a bias to the queries, keys and values. -
mask_token (
bool
, optional, defaults toTrue
) — Whether to use a mask token or not. Used in MIM (Masked Image Modeling) loss for FLAVA. -
vocab_size (
int
, optional, defaults to 8192) — Vocabulary size of the FlavaImageCodebook used in conjunction with FlavaImageModel for MIM (Masked Image Modeling) loss for FLAVA.
This is the configuration class to store the configuration of a FlavaImageModel. It is used to instantiate an FLAVA model according to the specified arguments, defining the model architecture.
Instantiating a configuration with the defaults will yield a similar configuration to that of the FLAVA facebook/flava-full architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
>>> from transformers import FlavaImageConfig, FlavaImageModel
>>> # Initializing a FlavaImageModel with style configuration
>>> configuration = FlavaImageConfig()
>>> # Initializing a FlavaImageModel model (with random weights) from the style configuration
>>> model = FlavaImageModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
FlavaMultimodalConfig
class transformers.FlavaMultimodalConfig
< source >( hidden_size: int = 768 num_hidden_layers: int = 6 num_attention_heads: int = 12 intermediate_size: int = 3072 hidden_act: int = 'gelu' hidden_dropout_prob: int = 0.0 attention_probs_dropout_prob: int = 0.0 initializer_range: float = 0.02 layer_norm_eps: float = 1e-12 qkv_bias: bool = True use_cls_token: bool = True **kwargs )
Parameters
- hidden_size (
int
, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer. - num_hidden_layers (
int
, optional, defaults to 12) — Number of hidden layers in the Transformer encoder. -
num_attention_heads (
int
, optional, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder. -
intermediate_size (
int
, optional, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder. - hidden_act (
str
orfunction
, optional, defaults to"gelu"
) — The non-linear activation function (function or string) in the encoder and pooler. If string,"gelu"
,"relu"
,"selu"
and"gelu_new"
are supported. - hidden_dropout_prob (
float
, optional, defaults to 0.1) — The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. -
attention_probs_dropout_prob (
float
, optional, defaults to 0.1) — The dropout ratio for the attention probabilities. -
initializer_range (
float
, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. -
layer_norm_eps (
float
, optional, defaults to 1e-12) — The epsilon used by the layer normalization layers. -
qkv_bias (
bool
, optional, defaults toTrue
) — Whether to add a bias to the queries, keys and values. -
use_cls_token (
bool
, optional, defaults toTrue
) — Whether to use an extra CLS token for multimodal settings. Usually needed by the FLAVA model.
This is the configuration class to store the configuration of a FlavaMultimodalModel. It is used to instantiate an FLAVA model according to the specified arguments, defining the model architecture.
Instantiating a configuration with the defaults will yield a similar configuration to that of the FLAVA facebook/flava-full architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
>>> from transformers import FlavaMultimodalConfig, FlavaMultimodalModel
>>> # Initializing a FlavaMultimodalModel with style configuration
>>> configuration = FlavaMultimodalConfig()
>>> # Initializing a FlavaMultimodalModel model (with random weights) from the style configuration
>>> model = FlavaMultimodalModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
FlavaImageCodebookConfig
class transformers.FlavaImageCodebookConfig
< source >( num_groups: int = 4 input_channels: int = 3 num_blocks_per_group: int = 2 hidden_size: int = 256 vocab_size: int = 8192 freeze: int = True initializer_range: float = 0.02 **kwargs )
FlavaProcessor
class transformers.FlavaProcessor
< source >( image_processor = None tokenizer = None **kwargs )
Parameters
- image_processor (FlavaImageProcessor) — The image processor is a required input.
- tokenizer (BertTokenizerFast) — The tokenizer is a required input.
Constructs a FLAVA processor which wraps a FLAVA image processor and a FLAVA tokenizer into a single processor.
FlavaProcessor offers all the functionalities of FlavaImageProcessor and BertTokenizerFast. See the
__call__()
and decode() for more information.
This method forwards all its arguments to BertTokenizerFastβs batch_decode(). Please refer to the docstring of this method for more information.
This method forwards all its arguments to BertTokenizerFastβs decode(). Please refer to the docstring of this method for more information.
FlavaFeatureExtractor
FlavaImageProcessor
class transformers.FlavaImageProcessor
< source >( do_resize: bool = True size: typing.Dict[str, int] = None resample: Resampling = <Resampling.BICUBIC: 3> do_center_crop: bool = True crop_size: typing.Dict[str, int] = None do_rescale: bool = True rescale_factor: typing.Union[int, float] = 0.00392156862745098 do_normalize: bool = True image_mean: typing.Union[float, typing.Iterable[float], NoneType] = None image_std: typing.Union[float, typing.Iterable[float], NoneType] = None return_image_mask: bool = False input_size_patches: int = 14 total_mask_patches: int = 75 mask_group_min_patches: int = 16 mask_group_max_patches: typing.Optional[int] = None mask_group_min_aspect_ratio: float = 0.3 mask_group_max_aspect_ratio: typing.Optional[float] = None return_codebook_pixels: bool = False codebook_do_resize: bool = True codebook_size: bool = None codebook_resample: int = <Resampling.LANCZOS: 1> codebook_do_center_crop: bool = True codebook_crop_size: int = None codebook_do_rescale: bool = True codebook_rescale_factor: typing.Union[int, float] = 0.00392156862745098 codebook_do_map_pixels: bool = True codebook_do_normalize: bool = True codebook_image_mean: typing.Union[float, typing.Iterable[float], NoneType] = None codebook_image_std: typing.Union[float, typing.Iterable[float], NoneType] = None **kwargs )
Parameters
-
do_resize (
bool
, optional, defaults toTrue
) — Whether to resize the image’s (height, width) dimensions to the specifiedsize
. Can be overridden by thedo_resize
parameter inpreprocess
. -
size (
Dict[str, int]
optional, defaults to{"height" -- 224, "width": 224}
): Size of the image after resizing. Can be overridden by thesize
parameter inpreprocess
. -
resample (
PILImageResampling
, optional, defaults toPILImageResampling.BICUBIC
) — Resampling filter to use if resizing the image. Can be overridden by theresample
parameter inpreprocess
. -
do_center_crop (
bool
, optional, defaults toTrue
) — Whether to center crop the images. Can be overridden by thedo_center_crop
parameter inpreprocess
. -
crop_size (
Dict[str, int]
optional, defaults to{"height" -- 224, "width": 224}
): Size of image after the center crop(crop_size["height"], crop_size["width"])
. Can be overridden by thecrop_size
parameter inpreprocess
. -
do_rescale (
bool
, optional, defaults toTrue
) — Whether to rescale the image by the specified scalerescale_factor
. Can be overridden by thedo_rescale
parameter inpreprocess
. -
rescale_factor (
int
orfloat
, optional, defaults to1/255
) — Scale factor to use if rescaling the image. Can be overridden by therescale_factor
parameter inpreprocess
. -
do_normalize (
bool
, optional, defaults toTrue
) — Whether to normalize the image. Can be overridden by thedo_normalize
parameter inpreprocess
. -
image_mean (
float
orList[float]
, optional, defaults toIMAGENET_STANDARD_MEAN
) — Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by theimage_mean
parameter in thepreprocess
method. -
image_std (
float
orList[float]
, optional, defaults toIMAGENET_STANDARD_STD
) — Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by theimage_std
parameter in thepreprocess
method. -
return_image_mask (
bool
, optional, defaults toFalse
) — Whether to return the image mask. Can be overridden by thereturn_image_mask
parameter inpreprocess
. -
input_size_patches (
int
, optional, defaults to 14) — Number of patches in the image in height and width direction. 14x14 = 196 total patches. Can be overridden by theinput_size_patches
parameter inpreprocess
. -
total_mask_patches (
int
, optional, defaults to 75) — Total number of patches that should be masked. Can be overridden by thetotal_mask_patches
parameter inpreprocess
. -
mask_group_min_patches (
int
, optional, defaults to 16) — Minimum number of patches that should be masked. Can be overridden by themask_group_min_patches
parameter inpreprocess
. -
mask_group_max_patches (
int
, optional) — Maximum number of patches that should be masked. Can be overridden by themask_group_max_patches
parameter inpreprocess
. -
mask_group_min_aspect_ratio (
float
, optional, defaults to 0.3) — Minimum aspect ratio of the mask window. Can be overridden by themask_group_min_aspect_ratio
parameter inpreprocess
. -
mask_group_max_aspect_ratio (
float
, optional) — Maximum aspect ratio of the mask window. Can be overridden by themask_group_max_aspect_ratio
parameter inpreprocess
. -
codebook_do_resize (
bool
, optional, defaults toTrue
) — Whether to resize the input for codebook to a certain. Can be overridden by thecodebook_do_resize
parameter inpreprocess
.codebook_size
. -
codebook_size (
Dict[str, int]
, optional, defaults to{"height" -- 224, "width": 224}
): Resize the input for codebook to the given size. Can be overridden by thecodebook_size
parameter inpreprocess
. -
codebook_resample (
PILImageResampling
, optional, defaults toPILImageResampling.LANCZOS
) — Resampling filter to use if resizing the codebook image. Can be overridden by thecodebook_resample
parameter inpreprocess
. -
codebook_do_center_crop (
bool
, optional, defaults toTrue
) — Whether to crop the input for codebook at the center. If the input size is smaller thancodebook_crop_size
along any edge, the image is padded with 0’s and then center cropped. Can be overridden by thecodebook_do_center_crop
parameter inpreprocess
. -
codebook_crop_size (
Dict[str, int]
, optional, defaults to{"height" -- 224, "width": 224}
): Desired output size for codebook input when applying center-cropping. Can be overridden by thecodebook_crop_size
parameter inpreprocess
. -
codebook_do_rescale (
bool
, optional, defaults toTrue
) — Whether to rescale the input for codebook by the specified scalecodebook_rescale_factor
. Can be overridden by thecodebook_do_rescale
parameter inpreprocess
. -
codebook_rescale_factor (
int
orfloat
, optional, defaults to1/255
) — Defines the scale factor to use if rescaling the codebook image. Can be overridden by thecodebook_rescale_factor
parameter inpreprocess
. -
codebook_do_map_pixels (
bool
, optional, defaults toTrue
) — Whether to map the pixel values of the codebook input to (1 - 2e)x + e. Can be overridden by thecodebook_do_map_pixels
parameter inpreprocess
. -
codebook_do_normalize (
bool
, optional, defaults toTrue
) — Whether or not to normalize the input for codebook withcodebook_image_mean
andcodebook_image_std
. Can be overridden by thecodebook_do_normalize
parameter inpreprocess
. -
codebook_image_mean (
Optional[Union[float, Iterable[float]]]
, optional, defaults to[0, 0, 0]
) — The sequence of means for each channel, to be used when normalizing images for codebook. Can be overridden by thecodebook_image_mean
parameter inpreprocess
. -
codebook_image_std (
Optional[Union[float, Iterable[float]]]
, optional, defaults to[0.5, 0.5, 0.5]
) — The sequence of standard deviations for each channel, to be used when normalizing images for codebook. Can be overridden by thecodebook_image_std
parameter inpreprocess
.
Constructs a Flava image processor.
preprocess
< source >( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[ForwardRef('PIL.Image.Image')], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]] do_resize: typing.Optional[bool] = None size: typing.Dict[str, int] = None resample: Resampling = None do_center_crop: typing.Optional[bool] = None crop_size: typing.Union[typing.Dict[str, int], NoneType] = None do_rescale: typing.Optional[bool] = None rescale_factor: typing.Optional[float] = None do_normalize: typing.Optional[bool] = None image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None return_image_mask: typing.Optional[bool] = None input_size_patches: typing.Optional[int] = None total_mask_patches: typing.Optional[int] = None mask_group_min_patches: typing.Optional[int] = None mask_group_max_patches: typing.Optional[int] = None mask_group_min_aspect_ratio: typing.Optional[float] = None mask_group_max_aspect_ratio: typing.Optional[float] = None return_codebook_pixels: typing.Optional[bool] = None codebook_do_resize: typing.Optional[bool] = None codebook_size: typing.Union[typing.Dict[str, int], NoneType] = None codebook_resample: typing.Optional[int] = None codebook_do_center_crop: typing.Optional[bool] = None codebook_crop_size: typing.Union[typing.Dict[str, int], NoneType] = None codebook_do_rescale: typing.Optional[bool] = None codebook_rescale_factor: typing.Optional[float] = None codebook_do_map_pixels: typing.Optional[bool] = None codebook_do_normalize: typing.Optional[bool] = None codebook_image_mean: typing.Optional[typing.Iterable[float]] = None codebook_image_std: typing.Optional[typing.Iterable[float]] = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None data_format: ChannelDimension = <ChannelDimension.FIRST: 'channels_first'> **kwargs )
Parameters
-
images (
ImageInput
) — Image to preprocess. -
do_resize (
bool
, optional, defaults toself.do_resize
) — Whether to resize the image. -
size (
Dict[str, int]
, optional, defaults toself.size
) — Size of the image. -
resample (
int
, optional, defaults toself.resample
) — Resampling filter to use if resizing the image. This can be one of the enumPILImageResampling
, Only has an effect ifdo_resize
is set toTrue
. -
do_center_crop (
bool
, optional, defaults toself.do_center_crop
) — Whether to center crop the image. -
crop_size (
Dict[str, int]
, optional, defaults toself.crop_size
) — Size of the center crop. Only has an effect ifdo_center_crop
is set toTrue
. -
do_rescale (
bool
, optional, defaults toself.do_rescale
) — Whether to rescale the image values between [0 - 1]. -
rescale_factor (
float
, optional, defaults toself.rescale_factor
) — Rescale factor to rescale the image by ifdo_rescale
is set toTrue
. -
do_normalize (
bool
, optional, defaults toself.do_normalize
) — Whether to normalize the image. -
image_mean (
float
orList[float]
, optional, defaults toself.image_mean
) — Image mean. -
image_std (
float
orList[float]
, optional, defaults toself.image_std
) — Image standard deviation. -
return_image_mask (
bool
, optional, defaults toself.return_image_mask
) — Whether to return the image mask. -
input_size_patches (
int
, optional, defaults toself.input_size_patches
) — Size of the patches to extract from the image. -
total_mask_patches (
int
, optional, defaults toself.total_mask_patches
) — Total number of patches to extract from the image. -
mask_group_min_patches (
int
, optional, defaults toself.mask_group_min_patches
) — Minimum number of patches to extract from the image. -
mask_group_max_patches (
int
, optional, defaults toself.mask_group_max_patches
) — Maximum number of patches to extract from the image. -
mask_group_min_aspect_ratio (
float
, optional, defaults toself.mask_group_min_aspect_ratio
) — Minimum aspect ratio of the patches to extract from the image. -
mask_group_max_aspect_ratio (
float
, optional, defaults toself.mask_group_max_aspect_ratio
) — Maximum aspect ratio of the patches to extract from the image. -
return_codebook_pixels (
bool
, optional, defaults toself.return_codebook_pixels
) — Whether to return the codebook pixels. -
codebook_do_resize (
bool
, optional, defaults toself.codebook_do_resize
) — Whether to resize the codebook pixels. -
codebook_size (
Dict[str, int]
, optional, defaults toself.codebook_size
) — Size of the codebook pixels. -
codebook_resample (
int
, optional, defaults toself.codebook_resample
) — Resampling filter to use if resizing the codebook pixels. This can be one of the enumPILImageResampling
, Only has an effect ifcodebook_do_resize
is set toTrue
. -
codebook_do_center_crop (
bool
, optional, defaults toself.codebook_do_center_crop
) — Whether to center crop the codebook pixels. -
codebook_crop_size (
Dict[str, int]
, optional, defaults toself.codebook_crop_size
) — Size of the center crop of the codebook pixels. Only has an effect ifcodebook_do_center_crop
is set toTrue
. -
codebook_do_rescale (
bool
, optional, defaults toself.codebook_do_rescale
) — Whether to rescale the codebook pixels values between [0 - 1]. -
codebook_rescale_factor (
float
, optional, defaults toself.codebook_rescale_factor
) — Rescale factor to rescale the codebook pixels by ifcodebook_do_rescale
is set toTrue
. -
codebook_do_map_pixels (
bool
, optional, defaults toself.codebook_do_map_pixels
) — Whether to map the codebook pixels values. -
codebook_do_normalize (
bool
, optional, defaults toself.codebook_do_normalize
) — Whether to normalize the codebook pixels. -
codebook_image_mean (
float
orList[float]
, optional, defaults toself.codebook_image_mean
) — Codebook pixels mean to normalize the codebook pixels by ifcodebook_do_normalize
is set toTrue
. -
codebook_image_std (
float
orList[float]
, optional, defaults toself.codebook_image_std
) — Codebook pixels standard deviation to normalize the codebook pixels by ifcodebook_do_normalize
is set toTrue
. -
return_tensors (
str
orTensorType
, optional) — The type of tensors to return. Can be one of:- Unset: Return a list of
np.ndarray
. TensorType.TENSORFLOW
or'tf'
: Return a batch of typetf.Tensor
.TensorType.PYTORCH
or'pt'
: Return a batch of typetorch.Tensor
.TensorType.NUMPY
or'np'
: Return a batch of typenp.ndarray
.TensorType.JAX
or'jax'
: Return a batch of typejax.numpy.ndarray
.
- Unset: Return a list of
-
data_format (
ChannelDimension
orstr
, optional, defaults toChannelDimension.FIRST
) — The channel dimension format for the output image. Can be one of:ChannelDimension.FIRST
: image in (num_channels, height, width) format.ChannelDimension.LAST
: image in (height, width, num_channels) format.
Preprocess an image or batch of images.
FlavaForPreTraining
class transformers.FlavaForPreTraining
< source >( config: FlavaConfig image_codebook: typing.Optional[torch.nn.modules.module.Module] = None )
Parameters
- config (FlavaConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
-
image_codebook (
nn.Module
) — If passed, the image codebook will be set to this. Otherwise. it will be initialized using the image_codebook_config defined in the config first as the first parameter.
The FLAVA model for pretraining which outputs losses, embeddings, logits and transformer outputs.
This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
input_ids_masked: typing.Optional[torch.LongTensor] = None
pixel_values: typing.Optional[torch.FloatTensor] = None
codebook_pixel_values: typing.Optional[torch.FloatTensor] = None
attention_mask: typing.Optional[torch.Tensor] = None
token_type_ids: typing.Optional[torch.Tensor] = None
bool_masked_pos: typing.Optional[torch.Tensor] = None
position_ids: typing.Optional[torch.LongTensor] = None
image_attention_mask: typing.Optional[torch.Tensor] = None
skip_unmasked_multimodal_encoder: bool = None
mlm_labels: typing.Optional[torch.Tensor] = None
mim_labels: typing.Optional[torch.Tensor] = None
itm_labels: typing.Optional[torch.Tensor] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: bool = True
return_dict: typing.Optional[bool] = None
return_loss: typing.Optional[bool] = None
)
β
transformers.models.flava.modeling_flava.FlavaForPreTrainingOutput
or tuple(torch.FloatTensor)
Parameters
-
input_ids_masked (
torch.LongTensor
of shape(batch_size, text_seq_len)
) — Indices of input sequence tokens in the vocabulary. These ones are the masked version of the original task to be used with MLM. Indices can be obtained using AutoTokenizer along withDataCollatorForMaskedLanguageModeling
. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are input IDs? -
input_ids (
torch.LongTensor
of shape(batch_size, text_seq_len)
) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are input IDs? -
token_type_ids (
torch.LongTensor
of shape(batch_size, text_seq_len)
, 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?
-
pixel_values (
torch.FloatTensor
of shape(batch_size, num_channels, height, width)
) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See FlavaImageProcessor.call() for details. -
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). -
interpolate_pos_encoding (
bool
, optional) — Whether to interpolate the pre-trained position encodings. -
image_attention_mask (
torch.FloatTensor
of shape(batch_size, image_num_patches)
, optional) — Mask to avoid performing attention on padding token indices specifically for images. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked. What are attention masks?
- skip_unmasked_multimodal_encoder (bool, optional) — Skip any calculations for multimodal encoder for unmasked inputs. FLAVA pretraining doesn’t need unmasked multimodal embeddings or outputs as of now.
-
mlm_labels (
torch.LongTensor
of shape(batch_size, text_seq_len)
, optional) — Labels for computing the left-to-right language and multimodal masked modeling loss (next word prediction). Indices should be in[-100, 0, ..., text_config.vocab_size - 1]
(seeinput_ids
docstring). Tokens with indices set to-100
are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., text_config.vocab_size - 1]
. -
mim_labels (
torch.LongTensor
of shape(batch_size, image_num_patches)
, optional) — Labels for computing the image and multimodal masked modeling loss. Indices should be in[-100, 0, ..., image_config.vocab_size - 1]
. Tokens with indices set to-100
are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., image_config.vocab_size - 1]
. If not passed, they are generated automatically using the image codebook assigned to the model. By default, it uses FlavaImageCodebook. See FlavaImageCodebook to understand how to generate mim_labels. -
itm_labels (
torch.LongTensor
of shape(batch_size, 1)
, optional) — Labels for computing the image-text matching loss. 0 means the pairs don’t match and 1 means they match. The pairs with 0 will be skipped for calculation of MMM and global contrastive losses as well. -
return_loss (
bool
, optional, default to None) — Whether to return calculated loss or not. -
attention_mask (
torch.FloatTensor
of shape(batch_size, text_seq_len)
, 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 tokens that are masked. What are attention masks?
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.Examples —
Returns
transformers.models.flava.modeling_flava.FlavaForPreTrainingOutput
or tuple(torch.FloatTensor)
A transformers.models.flava.modeling_flava.FlavaForPreTrainingOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (<class 'transformers.models.flava.configuration_flava.FlavaConfig'>
) and inputs.
-
loss (
torch.FloatTensor
, optional, returned whenreturn_loss
is True) β Total loss calculated for this model. -
loss_info (
FlavaLosses
) β Detailed info for FLAVA Pretraining losses. CheckFlavaLosses
class description for the information on the keys. -
image_embeddings (
torch.FloatTensor
of shape(batch_size, output_dim)
, optional, returned whenpixel_values
are present) β The image embeddings which are basically the pooled output of FlavaImageModel. -
image_output (
BaseModelOutputWithPooling
, optional, returned whenpixel_values
are present) β The output of the FlavaImageModel. -
text_embeddings (
torch.FloatTensor
of shape(batch_size, output_dim)
, optional, returned wheninput_ids
are present) β The text embeddings which are basically the pooled output of FlavaTextModel. -
text_output (
BaseModelOutputWithPooling
, optional, returned wheninput_ids
are present) β The output of the FlavaTextModel. -
multimodal_embeddings (
torch.FloatTensor
of shape(batch_size, output_dim)
, optional, returned wheninput_ids
andpixel_values
are present andskip_unmasked_multimodal_encoder
isNone
orFalse
) β The multimodal embeddings which are basically the pooled output of FlavaTextModel. -
multimodal_output (
BaseModelOutputWithPooling
, returned wheninput_ids
andpixel_values
are present andskip_unmasked_multimodal_encoder
isNone
orFalse
) β The output of the FlavaMultimodalModel. -
image_masked_embeddings (
torch.FloatTensor
of shape(batch_size, output_dim)
, optional, returned whenpixel_values
are present) β The image embeddings which are basically the pooled output of FlavaImageModel. Usesbool_masked_pos
to create masked images. -
image_masked_output (
BaseModelOutputWithPooling
, optional, returned whenpixel_values
are present) β The output of the FlavaImageModel. Usesbool_masked_pos
to create masked images. -
text_masked_embeddings (
torch.FloatTensor
of shape(batch_size, output_dim)
, optional, returned wheninput_ids_masked
are present) β The text embeddings which are basically the pooled output of FlavaTextModel. -
text_masked_output (
BaseModelOutputWithPooling
, optional, returned wheninput_ids_masked
are present) β The output of the FlavaTextModel. -
multimodal_masked_embeddings (
torch.FloatTensor
of shape(batch_size, output_dim)
, optional, returned wheninput_ids
andpixel_values
are present) β The multimodal embeddings which are basically the pooled output of FlavaTextModel. -
multimodal_masked_output (
BaseModelOutputWithPooling
, returned wheninput_ids_masked
andpixel_values
are present) β The output of the FlavaMultimodalModel. -
mim_logits (
torch.FloatTensor
of shape(batch_size, num_image_patches, image_vocab_size)
or of shape(total_masked_patches, image_vocab_size)
, optional, returned whenpixel_values
are present andinput_ids_masked
are not) β The logits for MIM unimodal loss. Usesbook_masked_pos
to get masked patches. The flattened output is returned whenbool_masked_pos
has some of the patches masked. -
mlm_logits (
torch.FloatTensor
of shape(batch_size, text_seq_length, text_vocab_size)
or of shape(total_masked_seq_length, text_vocab_size)
, optional, returned wheninput_ids_masked
are present andpixel_values
are not) β The logits for MLM unimodal loss. The flattened output is returned wheninput_ids_masked
has some of the tokens masked. -
itm_logits (
torch.FloatTensor
of shape(batch_size, 2)
, optional, returned wheninput_ids_masked
andpixel_values
are present) β The logits for ITM loss. Note that ITM loss is calculated on masked pairs in FLAVA. -
mmm_image_logits (
torch.FloatTensor
of shape(batch_size, num_image_patches, image_vocab_size)
or of shape(total_masked_patches, image_vocab_size)
, optional, returned whenpixel_values
andinput_ids_masked
are present) β The logits for MMM image multimodal loss. Usesbook_masked_pos
to get masked patches. The flattened output is returned whenbool_masked_pos
has some of the patches masked. -
mmm_text_logits (
torch.FloatTensor
of shape(batch_size, text_seq_length, text_vocab_size)
or of shape(
(total_masked_seq_length, text_vocab_size)), *optional*, returned when
pixel_valuesand
input_ids_maskedare present) -- The logits for MMM text multimodal loss. The flattened output is returned when
input_ids_masked` has some of the tokens masked. -
contrastive_logits_per_image (
torch.FloatTensor
of shape(image_batch_size, text_batch_size)
) β The scaled dot product scores betweenimage_embeddings
andtext_embeddings
but passed through FLAVAβsimage_projection
andtext_projection
layers respectively. This represents the image-text similarity scores. This is calculated on unmasked images and texts. -
contrastive_logits_per_text (
torch.FloatTensor
of shape(text_batch_size, image_batch_size)
) β The scaled dot product scores betweentext_embeddings
andimage_embeddings
but passed through FLAVAβstext_projection
andimage_projection
layers respectively. This is calculated on unmasked images and texts.
The FlavaForPreTraining forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
FlavaModel
class transformers.FlavaModel
< source >( config: FlavaConfig )
Parameters
- config (FlavaConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The bare FLAVA Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
pixel_values: typing.Optional[torch.FloatTensor] = None
attention_mask: typing.Optional[torch.Tensor] = None
token_type_ids: typing.Optional[torch.Tensor] = None
bool_masked_pos: typing.Optional[torch.Tensor] = None
position_ids: typing.Optional[torch.LongTensor] = None
image_attention_mask: typing.Optional[torch.Tensor] = None
skip_multimodal_encoder: typing.Optional[bool] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: bool = True
return_dict: typing.Optional[bool] = None
)
β
transformers.models.flava.modeling_flava.FlavaModelOutput
or tuple(torch.FloatTensor)
Parameters
-
pixel_values (
torch.FloatTensor
of shape(batch_size, num_channels, height, width)
) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See FlavaImageProcessor.call() for details. -
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). -
interpolate_pos_encoding (
bool
, optional) — Whether to interpolate the pre-trained position encodings. -
input_ids (
torch.LongTensor
of shape(batch_size, image_num_patches + text_seq_len)
) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are input IDs? -
token_type_ids (
torch.LongTensor
of shape(batch_size, image_num_patches + text_seq_len)
, 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?
-
attention_mask (
torch.FloatTensor
of shape(batch_size, image_num_patches + text_seq_len)
, 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 tokens that are masked. What are attention masks?
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - skip_multimodal_encoder (bool, optional) — Skip any calculations for multimodal encoder. Useful if multimodal encoding is not going to be used.
Returns
transformers.models.flava.modeling_flava.FlavaModelOutput
or tuple(torch.FloatTensor)
A transformers.models.flava.modeling_flava.FlavaModelOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (<class 'transformers.models.flava.configuration_flava.FlavaConfig'>
) and inputs.
- image_embeddings (
torch.FloatTensor
of shape(batch_size, output_dim)
, optional, returned whenpixel_values
are present) β The image embeddings which are basically the pooled output of FlavaImageModel. - image_output (
BaseModelOutputWithPooling
, optional, returned whenpixel_values
are present) β The output of the FlavaImageModel. - text_embeddings (
torch.FloatTensor
of shape(batch_size, output_dim)
, optional, returned wheninput_ids
are present) β The text embeddings which are basically the pooled output of FlavaTextModel. - text_output (
BaseModelOutputWithPooling
, optional, returned wheninput_ids
are present) β The output of the FlavaTextModel. - multimodal_embeddings (
torch.FloatTensor
of shape(batch_size, output_dim)
, optional, returned wheninput_ids
andpixel_values
are present andskip_multimodal_encoder
isNone
orFalse
) β The multimodal embeddings which are basically the pooled output of FlavaTextModel. - multimodal_output (
BaseModelOutputWithPooling
, returned wheninput_ids
andpixel_values
are present andskip_multimodal_encoder
isNone
orFalse
) β The output of the FlavaMultimodalModel.
The FlavaModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Examples:
>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, FlavaModel
>>> model = FlavaModel.from_pretrained("facebook/flava-full")
>>> processor = AutoProcessor.from_pretrained("facebook/flava-full")
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = processor(text=["a photo of a cat"], images=image, return_tensors="pt", padding=True)
>>> outputs = model(**inputs)
>>> logits_per_image = outputs.contrastive_logits_per_image # this is the image-text similarity score
>>> probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities
get_text_features
< source >( input_ids: typing.Optional[torch.Tensor] = None attention_mask: typing.Optional[torch.Tensor] = None token_type_ids: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None )
Parameters
-
input_ids (
torch.LongTensor
of shape(batch_size, text_seq_length)
) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are input IDs? -
token_type_ids (
torch.LongTensor
of shape(batch_size, text_seq_length)
, 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?
-
attention_mask (
torch.FloatTensor
of shape(batch_size, text_seq_length)
, 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 tokens that are masked. What are attention masks?
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
The FlavaModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
get_image_features
< source >( pixel_values: typing.Optional[torch.Tensor] = None bool_masked_pos: typing.Optional[torch.BoolTensor] = None interpolate_pos_encoding: typing.Optional[bool] = None attention_mask: typing.Optional[torch.Tensor] = None head_mask: typing.Optional[torch.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None )
Parameters
-
pixel_values (
torch.FloatTensor
of shape(batch_size, num_channels, height, width)
) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See FlavaImageProcessor.call() for details. -
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). -
interpolate_pos_encoding (
bool
, optional) — Whether to interpolate the pre-trained position encodings. -
attention_mask (
torch.FloatTensor
of shape(batch_size, image_num_patches)
, 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 tokens that are masked. What are attention masks?
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
The FlavaModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
FlavaImageCodebook
class transformers.FlavaImageCodebook
< source >( config: FlavaImageCodebookConfig **kwargs: typing.Any )
Parameters
- config (FlavaImageCodebookConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The FLAVAβs image codebook model inspired from DALL-Eβs original encoder. Outputs raw hidden states and can be used
to generate image tokens for an image based on DALL-Eβs vocab. Used to generate labels for MIM. Use
get_codebook_indices
to get image tokens for an image.
This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
FlavaTextModel
class transformers.FlavaTextModel
< source >( config: FlavaTextConfig add_pooling_layer: bool = True )
Parameters
- config (FlavaTextConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The bare FLAVA Text Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >(
input_ids: typing.Optional[torch.Tensor] = None
attention_mask: typing.Optional[torch.Tensor] = None
token_type_ids: typing.Optional[torch.Tensor] = None
position_ids: typing.Optional[torch.Tensor] = None
head_mask: typing.Optional[torch.Tensor] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
)
β
transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
Parameters
-
input_ids (
torch.LongTensor
of shape(batch_size, text_seq_length)
) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are input IDs? -
token_type_ids (
torch.LongTensor
of shape(batch_size, text_seq_length)
, 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?
-
attention_mask (
torch.FloatTensor
of shape(batch_size, text_seq_length)
, 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 tokens that are masked. What are attention masks?
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
A transformers.modeling_outputs.BaseModelOutputWithPooling or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (FlavaTextConfig) and inputs.
-
last_hidden_state (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model. -
pooler_output (
torch.FloatTensor
of shape(batch_size, hidden_size)
) β Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The FlavaTextModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import AutoTokenizer, FlavaTextModel
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/flava-full")
>>> model = FlavaTextModel.from_pretrained("facebook/flava-full")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
FlavaImageModel
class transformers.FlavaImageModel
< source >( config: FlavaImageConfig add_pooling_layer: bool = True )
Parameters
- config (FlavaImageConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The bare FLAVA Image Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >(
pixel_values: typing.Optional[torch.Tensor] = None
bool_masked_pos: typing.Optional[torch.BoolTensor] = None
interpolate_pos_encoding: typing.Optional[bool] = None
attention_mask: typing.Optional[torch.Tensor] = None
head_mask: typing.Optional[torch.Tensor] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
)
β
transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
Parameters
-
pixel_values (
torch.FloatTensor
of shape(batch_size, num_channels, height, width)
) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See FlavaImageProcessor.call() for details. -
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). -
interpolate_pos_encoding (
bool
, optional) — Whether to interpolate the pre-trained position encodings. -
attention_mask (
torch.FloatTensor
of shape(batch_size, image_num_patches)
, 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 tokens that are masked. What are attention masks?
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
A transformers.modeling_outputs.BaseModelOutputWithPooling or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (FlavaImageConfig) and inputs.
-
last_hidden_state (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model. -
pooler_output (
torch.FloatTensor
of shape(batch_size, hidden_size)
) β Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The FlavaImageModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import AutoImageProcessor, FlavaImageModel
>>> import torch
>>> from datasets import load_dataset
>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]
>>> image_processor = AutoImageProcessor.from_pretrained("facebook/flava-full")
>>> model = FlavaImageModel.from_pretrained("facebook/flava-full")
>>> inputs = image_processor(image, return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 197, 768]
FlavaMultimodalModel
class transformers.FlavaMultimodalModel
< source >( config: FlavaMultimodalConfig add_pooling_layer = True )
Parameters
- config (FlavaMultimodalConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The bare FLAVA Multimodal Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >(
hidden_states: Tensor
attention_mask: typing.Optional[torch.Tensor] = None
head_mask: typing.Optional[torch.Tensor] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
)
β
transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
Parameters
- hidden_states (
torch.FloatTensor
of shape(batch_size, image_num_patches + text_seq_len, hidden_size)
) — The concatenated hidden states of unimodal encoders. -
attention_mask (
torch.FloatTensor
of shape(batch_size, image_num_patches + text_seq_len)
, 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 tokens that are masked. What are attention masks?
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
A transformers.modeling_outputs.BaseModelOutputWithPooling or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (FlavaMultimodalConfig) and inputs.
-
last_hidden_state (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model. -
pooler_output (
torch.FloatTensor
of shape(batch_size, hidden_size)
) β Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The FlavaMultimodalModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import AutoTokenizer, FlavaMultimodalModel
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/flava-full")
>>> model = FlavaMultimodalModel.from_pretrained("facebook/flava-full")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state