# BridgeTower ## Overview The BridgeTower model was proposed in [BridgeTower: Building Bridges Between Encoders in Vision-Language Representative Learning](https://huggingface.co/papers/2206.08657) by Xiao Xu, Chenfei Wu, Shachar Rosenman, Vasudev Lal, Wanxiang Che, Nan Duan. The goal of this model is to build a bridge between each uni-modal encoder and the cross-modal encoder to enable comprehensive and detailed interaction at each layer of the cross-modal encoder thus achieving remarkable performance on various downstream tasks with almost negligible additional performance and computational costs. This paper has been accepted to the [AAAI'23](https://aaai.org/Conferences/AAAI-23/) conference. The abstract from the paper is the following: *Vision-Language (VL) models with the TWO-TOWER architecture have dominated visual-language representation learning in recent years. Current VL models either use lightweight uni-modal encoders and learn to extract, align and fuse both modalities simultaneously in a deep cross-modal encoder, or feed the last-layer uni-modal representations from the deep pre-trained uni-modal encoders into the top cross-modal encoder. Both approaches potentially restrict vision-language representation learning and limit model performance. In this paper, we propose BRIDGETOWER, which introduces multiple bridge layers that build a connection between the top layers of uni-modal encoders and each layer of the crossmodal encoder. This enables effective bottom-up cross-modal alignment and fusion between visual and textual representations of different semantic levels of pre-trained uni-modal encoders in the cross-modal encoder. Pre-trained with only 4M images, BRIDGETOWER achieves state-of-the-art performance on various downstream vision-language tasks. In particular, on the VQAv2 test-std set, BRIDGETOWER achieves an accuracy of 78.73%, outperforming the previous state-of-the-art model METER by 1.09% with the same pre-training data and almost negligible additional parameters and computational costs. Notably, when further scaling the model, BRIDGETOWER achieves an accuracy of 81.15%, surpassing models that are pre-trained on orders-of-magnitude larger datasets.* BridgeTower architecture. Taken from the original paper. This model was contributed by [Anahita Bhiwandiwalla](https://huggingface.co/anahita-b), [Tiep Le](https://huggingface.co/Tile) and [Shaoyen Tseng](https://huggingface.co/shaoyent). The original code can be found [here](https://github.com/microsoft/BridgeTower). ## Usage tips and examples BridgeTower consists of a visual encoder, a textual encoder and cross-modal encoder with multiple lightweight bridge layers. The goal of this approach was to build a bridge between each uni-modal encoder and the cross-modal encoder to enable comprehensive and detailed interaction at each layer of the cross-modal encoder. In principle, one can apply any visual, textual or cross-modal encoder in the proposed architecture. The [BridgeTowerProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) wraps [RobertaTokenizer](/docs/transformers/v5.2.0/en/model_doc/mvp#transformers.RobertaTokenizer) and [BridgeTowerImageProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessor) into a single instance to both encode the text and prepare the images respectively. The following example shows how to run contrastive learning using [BridgeTowerProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) and [BridgeTowerForContrastiveLearning](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerForContrastiveLearning). ```python >>> from transformers import BridgeTowerProcessor, BridgeTowerForContrastiveLearning >>> import requests >>> from PIL import Image >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> image = Image.open(requests.get(url, stream=True).raw) >>> texts = ["An image of two cats chilling on a couch", "A football player scoring a goal"] >>> processor = BridgeTowerProcessor.from_pretrained("BridgeTower/bridgetower-large-itm-mlm-itc") >>> model = BridgeTowerForContrastiveLearning.from_pretrained("BridgeTower/bridgetower-large-itm-mlm-itc") >>> # forward pass >>> scores = dict() >>> for text in texts: ... # prepare inputs ... encoding = processor(image, text, return_tensors="pt") ... outputs = model(**encoding) ... scores[text] = outputs ``` The following example shows how to run image-text retrieval using [BridgeTowerProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) and [BridgeTowerForImageAndTextRetrieval](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerForImageAndTextRetrieval). ```python >>> from transformers import BridgeTowerProcessor, BridgeTowerForImageAndTextRetrieval >>> import requests >>> from PIL import Image >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> image = Image.open(requests.get(url, stream=True).raw) >>> texts = ["An image of two cats chilling on a couch", "A football player scoring a goal"] >>> processor = BridgeTowerProcessor.from_pretrained("BridgeTower/bridgetower-base-itm-mlm") >>> model = BridgeTowerForImageAndTextRetrieval.from_pretrained("BridgeTower/bridgetower-base-itm-mlm") >>> # forward pass >>> scores = dict() >>> for text in texts: ... # prepare inputs ... encoding = processor(image, text, return_tensors="pt") ... outputs = model(**encoding) ... scores[text] = outputs.logits[0, 1].item() ``` The following example shows how to run masked language modeling using [BridgeTowerProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) and [BridgeTowerForMaskedLM](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerForMaskedLM). ```python >>> from transformers import BridgeTowerProcessor, BridgeTowerForMaskedLM >>> from PIL import Image >>> import requests >>> url = "http://images.cocodataset.org/val2017/000000360943.jpg" >>> image = Image.open(requests.get(url, stream=True).raw).convert("RGB") >>> text = "a looking out of the window" >>> processor = BridgeTowerProcessor.from_pretrained("BridgeTower/bridgetower-base-itm-mlm") >>> model = BridgeTowerForMaskedLM.from_pretrained("BridgeTower/bridgetower-base-itm-mlm") >>> # prepare inputs >>> encoding = processor(image, text, return_tensors="pt") >>> # forward pass >>> outputs = model(**encoding) >>> results = processor.decode(outputs.logits.argmax(dim=-1).squeeze(0).tolist()) >>> print(results) .a cat looking out of the window. ``` Tips: - This implementation of BridgeTower uses [RobertaTokenizer](/docs/transformers/v5.2.0/en/model_doc/mvp#transformers.RobertaTokenizer) to generate text embeddings and OpenAI's CLIP/ViT model to compute visual embeddings. - Checkpoints for pre-trained [bridgeTower-base](https://huggingface.co/BridgeTower/bridgetower-base) and [bridgetower masked language modeling and image text matching](https://huggingface.co/BridgeTower/bridgetower-base-itm-mlm) are released. - Please refer to [Table 5](https://huggingface.co/papers/2206.08657) for BridgeTower's performance on Image Retrieval and other down stream tasks. ## BridgeTowerConfig[[transformers.BridgeTowerConfig]] #### transformers.BridgeTowerConfig[[transformers.BridgeTowerConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/configuration_bridgetower.py#L200) This is the configuration class to store the configuration of a [BridgeTowerModel](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerModel). It is used to instantiate a BridgeTower 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 bridgetower-base [BridgeTower/bridgetower-base](https://huggingface.co/BridgeTower/bridgetower-base/) architecture. Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.2.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.2.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import BridgeTowerModel, BridgeTowerConfig >>> # Initializing a BridgeTower BridgeTower/bridgetower-base style configuration >>> configuration = BridgeTowerConfig() >>> # Initializing a model from the BridgeTower/bridgetower-base style configuration >>> model = BridgeTowerModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** share_cross_modal_transformer_layers (`bool`, *optional*, defaults to `True`) : Whether cross modal transformer layers are shared. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`) : The non-linear activation function (function or string) in the encoder and pooler. hidden_size (`int`, *optional*, defaults to 768) : Dimensionality of the encoder layers and the pooler layer. initializer_factor (`float`, *optional*, defaults to 1) : A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). layer_norm_eps (`float`, *optional*, defaults to 1e-05) : The epsilon used by the layer normalization layers. share_link_tower_layers (`bool`, *optional*, defaults to `False`) : Whether the bride/link tower layers are shared. link_tower_type (`str`, *optional*, defaults to `"add"`) : Type of the bridge/link layer. num_attention_heads (`int`, *optional*, defaults to 12) : Number of attention heads for each attention layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 6) : Number of hidden layers in the Transformer encoder. tie_word_embeddings (`bool`, *optional*, defaults to `False`) : Whether to tie input and output embeddings. init_layernorm_from_vision_encoder (`bool`, *optional*, defaults to `False`) : Whether to init LayerNorm from the vision encoder. text_config (`dict`, *optional*) : Dictionary of configuration options used to initialize [BridgeTowerTextConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerTextConfig). vision_config (`dict`, *optional*) : Dictionary of configuration options used to initialize [BridgeTowerVisionConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerVisionConfig). ## BridgeTowerTextConfig[[transformers.BridgeTowerTextConfig]] #### transformers.BridgeTowerTextConfig[[transformers.BridgeTowerTextConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/configuration_bridgetower.py#L96) This is the configuration class to store the text configuration of a [BridgeTowerModel](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerModel). The default values here are copied from RoBERTa. Instantiating a configuration with the defaults will yield a similar configuration to that of the bridgetower-base [BridegTower/bridgetower-base](https://huggingface.co/BridgeTower/bridgetower-base/) architecture. Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.2.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.2.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import BridgeTowerTextConfig >>> # Initializing a BridgeTower BridgeTower/bridgetower-base style configuration for the text model >>> configuration = BridgeTowerTextConfig() >>> # Accessing the configuration >>> configuration ``` **Parameters:** vocab_size (`int`, *optional*, defaults to 50265) : Vocabulary size of the text part of the model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [BridgeTowerModel](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerModel). 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" (often named feed-forward) layer in the Transformer encoder. hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`) : The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1) : The dropout probability 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. max_position_embeddings (`int`, *optional*, defaults to 514) : 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). type_vocab_size (`int`, *optional*, defaults to 2) : The vocabulary size of the `token_type_ids`. initializer_factor (`float`, *optional*, defaults to 1) : A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). layer_norm_eps (`float`, *optional*, defaults to 1e-05) : The epsilon used by the layer normalization layers. is_decoder (`bool`, *optional*, defaults to `False`) : Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. use_cache (`bool`, *optional*, defaults to `True`) : Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. ## BridgeTowerVisionConfig[[transformers.BridgeTowerVisionConfig]] #### transformers.BridgeTowerVisionConfig[[transformers.BridgeTowerVisionConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/configuration_bridgetower.py#L23) This is the configuration class to store the vision configuration of a [BridgeTowerModel](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerModel). Instantiating a configuration with the defaults will yield a similar configuration to that of the bridgetower-base [BridgeTower/bridgetower-base](https://huggingface.co/BridgeTower/bridgetower-base/) architecture. Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.2.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.2.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import BridgeTowerVisionConfig >>> # Initializing a BridgeTower BridgeTower/bridgetower-base style configuration for the vision model >>> configuration = BridgeTowerVisionConfig() >>> # Accessing the configuration >>> configuration ``` **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 visual encoder model. patch_size (`int`, *optional*, defaults to 16) : The size (resolution) of each patch. image_size (`int`, *optional*, defaults to 288) : The size (resolution) of each image. initializer_factor (`float`, *optional*, defaults to 1) : A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). layer_norm_eps (`float`, *optional*, defaults to 1e-05) : The epsilon used by the layer normalization layers. stop_gradient (`bool`, *optional*, defaults to `False`) : Whether to stop gradient for training. share_layernorm (`bool`, *optional*, defaults to `True`) : Whether LayerNorm layers are shared. remove_last_layer (`bool`, *optional*, defaults to `False`) : Whether to remove the last layer from the vision encoder. ## BridgeTowerImageProcessor[[transformers.BridgeTowerImageProcessor]] #### transformers.BridgeTowerImageProcessor[[transformers.BridgeTowerImageProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/image_processing_bridgetower.py#L129) Constructs a BridgeTower image processor. preprocesstransformers.BridgeTowerImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/image_processing_bridgetower.py#L374[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "do_resize", "val": ": bool | None = None"}, {"name": "size", "val": ": dict[str, int] | None = None"}, {"name": "size_divisor", "val": ": int | None = None"}, {"name": "resample", "val": ": PIL.Image.Resampling | None = None"}, {"name": "do_rescale", "val": ": bool | None = None"}, {"name": "rescale_factor", "val": ": float | None = None"}, {"name": "do_normalize", "val": ": bool | None = None"}, {"name": "image_mean", "val": ": float | list[float] | None = None"}, {"name": "image_std", "val": ": float | list[float] | None = None"}, {"name": "do_pad", "val": ": bool | None = None"}, {"name": "do_center_crop", "val": ": bool | None = None"}, {"name": "crop_size", "val": ": dict[str, int] | None = None"}, {"name": "return_tensors", "val": ": str | transformers.utils.generic.TensorType | None = None"}, {"name": "data_format", "val": ": ChannelDimension = "}, {"name": "input_data_format", "val": ": str | transformers.image_utils.ChannelDimension | None = None"}]- **images** (`ImageInput`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **do_resize** (`bool`, *optional*, defaults to `self.do_resize`) -- Whether to resize the image. - **size** (`dict[str, int]`, *optional*, defaults to `self.size`) -- Controls the size of the image after `resize`. The shortest edge of the image is resized to `size["shortest_edge"]` whilst preserving the aspect ratio. If the longest edge of this resized image is > `int(size["shortest_edge"] * (1333 / 800))`, then the image is resized again to make the longest edge equal to `int(size["shortest_edge"] * (1333 / 800))`. - **size_divisor** (`int`, *optional*, defaults to `self.size_divisor`) -- The image is resized to a size that is a multiple of this value. - **resample** (`PILImageResampling`, *optional*, defaults to `self.resample`) -- Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. - **do_rescale** (`bool`, *optional*, defaults to `self.do_rescale`) -- Whether to rescale the image values between [0 - 1]. - **rescale_factor** (`float`, *optional*, defaults to `self.rescale_factor`) -- Rescale factor to rescale the image by if `do_rescale` is set to `True`. - **do_normalize** (`bool`, *optional*, defaults to `self.do_normalize`) -- Whether to normalize the image. - **image_mean** (`float` or `list[float]`, *optional*, defaults to `self.image_mean`) -- Image mean to normalize the image by if `do_normalize` is set to `True`. - **image_std** (`float` or `list[float]`, *optional*, defaults to `self.image_std`) -- Image standard deviation to normalize the image by if `do_normalize` is set to `True`. - **do_pad** (`bool`, *optional*, defaults to `self.do_pad`) -- Whether to pad the image to the (max_height, max_width) in the batch. If `True`, a pixel mask is also created and returned. - **do_center_crop** (`bool`, *optional*, defaults to `self.do_center_crop`) -- Whether to center crop the image. If the input size is smaller than `crop_size` along any edge, the image is padded with 0's and then center cropped. - **crop_size** (`dict[str, int]`, *optional*, defaults to `self.crop_size`) -- Size of the image after center crop. If one edge the image is smaller than `crop_size`, it will be padded with zeros and then cropped - **return_tensors** (`str` or `TensorType`, *optional*) -- The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`. - **data_format** (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`) -- The channel dimension format for the output image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - Unset: Use the channel dimension format of the input image. - **input_data_format** (`ChannelDimension` or `str`, *optional*) -- The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.0 Preprocess an image or batch of images. **Parameters:** do_resize (`bool`, *optional*, defaults to `True`) : Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`dict[str, int]` *optional*, defaults to `{'shortest_edge' : 288}`): Resize the shorter side of the input to `size["shortest_edge"]`. The longer side will be limited to under `int((1333 / 800) * size["shortest_edge"])` while preserving the aspect ratio. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `size` parameter in the `preprocess` method. size_divisor (`int`, *optional*, defaults to 32) : The size by which to make sure both the height and width can be divided. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `size_divisor` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`) : Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `resample` parameter in the `preprocess` method. do_rescale (`bool`, *optional*, defaults to `True`) : Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`) : Scale factor to use if rescaling the image. Only has an effect if `do_rescale` is set to `True`. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`) : Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `IMAGENET_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 the `image_mean` parameter in the `preprocess` method. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `list[float]`, *optional*, defaults to `IMAGENET_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 the `image_std` parameter in the `preprocess` method. Can be overridden by the `image_std` parameter in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `True`) : Whether to center crop the image. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`dict[str, int]`, *optional*) : Desired output size when applying center-cropping. Only has an effect if `do_center_crop` is set to `True`. Can be overridden by the `crop_size` parameter in the `preprocess` method. If unset defaults to `size`, do_pad (`bool`, *optional*, defaults to `True`) : Whether to pad the image to the `(max_height, max_width)` of the images in the batch. Can be overridden by the `do_pad` parameter in the `preprocess` method. ## BridgeTowerImageProcessorFast[[transformers.BridgeTowerImageProcessorFast]] #### transformers.BridgeTowerImageProcessorFast[[transformers.BridgeTowerImageProcessorFast]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/image_processing_bridgetower_fast.py#L88) Constructs a fast Bridgetower image processor. preprocesstransformers.BridgeTowerImageProcessorFast.preprocesshttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/image_processing_bridgetower_fast.py#L107[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.models.bridgetower.image_processing_bridgetower.BridgeTowerImageProcessorKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list, list, list]`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **do_convert_rgb** (`bool | None.do_convert_rgb`) -- Whether to convert the image to RGB. - **do_resize** (`bool | None.do_resize`) -- Whether to resize the image. - **size** (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) -- Describes the maximum input dimensions to the model. - **crop_size** (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) -- Size of the output image after applying `center_crop`. - **resample** (`Annotated[Union[PILImageResampling, int, NoneType], None]`) -- Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`. Only has an effect if `do_resize` is set to `True`. - **do_rescale** (`bool | None.do_rescale`) -- Whether to rescale the image. - **rescale_factor** (`float | None.rescale_factor`) -- Rescale factor to rescale the image by if `do_rescale` is set to `True`. - **do_normalize** (`bool | None.do_normalize`) -- Whether to normalize the image. - **image_mean** (`float | list[float] | tuple[float, ...] | None.image_mean`) -- Image mean to use for normalization. Only has an effect if `do_normalize` is set to `True`. - **image_std** (`float | list[float] | tuple[float, ...] | None.image_std`) -- Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to `True`. - **do_pad** (`bool | None.do_pad`) -- Whether to pad the image. Padding is done either to the largest size in the batch or to a fixed square size per image. The exact padding strategy depends on the model. - **pad_size** (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) -- The size in `{"height": int, "width" int}` to pad the images to. Must be larger than any image size provided for preprocessing. If `pad_size` is not provided, images will be padded to the largest height and width in the batch. Applied only when `do_pad=True.` - **do_center_crop** (`bool | None.do_center_crop`) -- Whether to center crop the image. - **data_format** (`str | ~image_utils.ChannelDimension | None.data_format`) -- Only `ChannelDimension.FIRST` is supported. Added for compatibility with slow processors. - **input_data_format** (`str | ~image_utils.ChannelDimension | None.input_data_format`) -- The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. - **device** (`Annotated[Union[str, torch.device, NoneType], None]`) -- The device to process the images on. If unset, the device is inferred from the input images. - **return_tensors** (`Annotated[str | ~utils.generic.TensorType | None, None]`) -- Returns stacked tensors if set to `pt, otherwise returns a list of tensors. - **disable_grouping** (`bool | None.disable_grouping`) -- Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - **image_seq_length** (`int | None.image_seq_length`) -- The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. - **size_divisor** (`.size_divisor`) -- The size by which to make sure both the height and width can be divided.0``- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** images (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list, list, list]`) : Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. do_convert_rgb (`bool | None.do_convert_rgb`) : Whether to convert the image to RGB. do_resize (`bool | None.do_resize`) : Whether to resize the image. size (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) : Describes the maximum input dimensions to the model. crop_size (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) : Size of the output image after applying `center_crop`. resample (`Annotated[Union[PILImageResampling, int, NoneType], None]`) : Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`. Only has an effect if `do_resize` is set to `True`. do_rescale (`bool | None.do_rescale`) : Whether to rescale the image. rescale_factor (`float | None.rescale_factor`) : Rescale factor to rescale the image by if `do_rescale` is set to `True`. do_normalize (`bool | None.do_normalize`) : Whether to normalize the image. image_mean (`float | list[float] | tuple[float, ...] | None.image_mean`) : Image mean to use for normalization. Only has an effect if `do_normalize` is set to `True`. image_std (`float | list[float] | tuple[float, ...] | None.image_std`) : Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to `True`. do_pad (`bool | None.do_pad`) : Whether to pad the image. Padding is done either to the largest size in the batch or to a fixed square size per image. The exact padding strategy depends on the model. pad_size (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) : The size in `{"height": int, "width" int}` to pad the images to. Must be larger than any image size provided for preprocessing. If `pad_size` is not provided, images will be padded to the largest height and width in the batch. Applied only when `do_pad=True.` do_center_crop (`bool | None.do_center_crop`) : Whether to center crop the image. data_format (`str | ~image_utils.ChannelDimension | None.data_format`) : Only `ChannelDimension.FIRST` is supported. Added for compatibility with slow processors. input_data_format (`str | ~image_utils.ChannelDimension | None.input_data_format`) : The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. device (`Annotated[Union[str, torch.device, NoneType], None]`) : The device to process the images on. If unset, the device is inferred from the input images. return_tensors (`Annotated[str | ~utils.generic.TensorType | None, None]`) : Returns stacked tensors if set to `pt, otherwise returns a list of tensors. disable_grouping (`bool | None.disable_grouping`) : Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 image_seq_length (`int | None.image_seq_length`) : The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. size_divisor (`.size_divisor`) : The size by which to make sure both the height and width can be divided. **Returns:** ```` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. ## BridgeTowerProcessor[[transformers.BridgeTowerProcessor]] #### transformers.BridgeTowerProcessor[[transformers.BridgeTowerProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/processing_bridgetower.py#L42) Constructs a BridgeTowerProcessor which wraps a image processor and a tokenizer into a single processor. [BridgeTowerProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) offers all the functionalities of [BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast) and [RobertaTokenizer](/docs/transformers/v5.2.0/en/model_doc/mvp#transformers.RobertaTokenizer). See the [~BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast) and [~RobertaTokenizer](/docs/transformers/v5.2.0/en/model_doc/mvp#transformers.RobertaTokenizer) for more information. __call__transformers.BridgeTowerProcessor.__call__https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/processing_utils.py#L603[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None"}, {"name": "text", "val": ": str | list[str] | list[list[str]] | None = None"}, {"name": "videos", "val": ": typing.Union[list['PIL.Image.Image'], numpy.ndarray, ForwardRef('torch.Tensor'), list[numpy.ndarray], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list[numpy.ndarray]], list[list['torch.Tensor']], transformers.video_utils.URL, list[transformers.video_utils.URL], list[list[transformers.video_utils.URL]], transformers.video_utils.Path, list[transformers.video_utils.Path], list[list[transformers.video_utils.Path]], NoneType] = None"}, {"name": "audio", "val": ": typing.Union[numpy.ndarray, ForwardRef('torch.Tensor'), collections.abc.Sequence[numpy.ndarray], collections.abc.Sequence['torch.Tensor'], NoneType] = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ProcessingKwargs]"}]- **images** (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `list[PIL.Image.Image]`, `list[np.ndarray]`, `list[torch.Tensor]`) -- The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported. - **text** (`TextInput`, `PreTokenizedInput`, `list[TextInput]`, `list[PreTokenizedInput]`, *optional*) -- The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences). - **videos** (`np.ndarray`, `torch.Tensor`, `List[np.ndarray]`, `List[torch.Tensor]`) -- The video or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported. - **audio** (`np.ndarray`, `torch.Tensor`, `list[np.ndarray]`, `list[torch.Tensor]`) -- The audio or batch of audio to be prepared. Each audio can be a NumPy array or PyTorch tensor. - **return_tensors** (`str` or [TensorType](/docs/transformers/v5.2.0/en/internal/file_utils#transformers.TensorType), *optional*) -- If set, will return tensors of a particular framework. Acceptable values are: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects.0[BatchFeature](/docs/transformers/v5.2.0/en/main_classes/feature_extractor#transformers.BatchFeature)A [BatchFeature](/docs/transformers/v5.2.0/en/main_classes/feature_extractor#transformers.BatchFeature) object with processed inputs in a dict format. Main method to prepare for model inputs. This method forwards the each modality argument to its own processor along with `kwargs`. Please refer to the docstring of the each processor attributes for more information. **Parameters:** image_processor (`BridgeTowerImageProcessorFast`) : The image processor is a required input. tokenizer (`RobertaTokenizer`) : The tokenizer is a required input. **Returns:** `[BatchFeature](/docs/transformers/v5.2.0/en/main_classes/feature_extractor#transformers.BatchFeature)` A [BatchFeature](/docs/transformers/v5.2.0/en/main_classes/feature_extractor#transformers.BatchFeature) object with processed inputs in a dict format. ## BridgeTowerModel[[transformers.BridgeTowerModel]] #### transformers.BridgeTowerModel[[transformers.BridgeTowerModel]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/modeling_bridgetower.py#L1150) The bare BridgeTower Model transformer outputting BridgeTowerModelOutput object without any specific head on This model inherits from [PreTrainedModel](/docs/transformers/v5.2.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.BridgeTowerModel.forwardhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/modeling_bridgetower.py#L1213[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "pixel_mask", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "image_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "image_token_type_idx", "val": ": int | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.2.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.2.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.2.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_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?](../glossary#token-type-ids) - **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast). See [BridgeTowerImageProcessorFast.__call__()](/docs/transformers/v5.2.0/en/model_doc/fuyu#transformers.FuyuImageProcessor.__call__) for details ([BridgeTowerProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) uses [BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast) for processing images). - **pixel_mask** (`torch.LongTensor` of shape `(batch_size, height, width)`, *optional*) -- Mask to avoid performing attention on padding pixel values. Mask values selected in `[0, 1]`: - 1 for pixels that are real (i.e. **not masked**), - 0 for pixels that are padding (i.e. **masked**). [What are attention masks?](../glossary#attention-mask) - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **image_embeds** (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`, *optional*) -- Optionally, instead of passing `pixel_values`, you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `pixel_values` into patch embeddings. - **image_token_type_idx** (`int`, *optional*) -- - The token type ids for images. - **output_attentions** (`bool`, *optional*) -- Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. - **output_hidden_states** (`bool`, *optional*) -- If set to `True`, hidden states are returned as a list containing the hidden states of text, image, and cross-modal components respectively. i.e. `(hidden_states_text, hidden_states_image, hidden_states_cross_modal)` where each element is a list of the hidden states of the corresponding modality. `hidden_states_txt/img` are a list of tensors corresponding to unimodal hidden states and `hidden_states_cross_modal` is a list of tuples containing `cross_modal_text_hidden_states` and `cross_modal_image_hidden_states` of each brdige layer. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. - **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) -- Labels are currently not supported. - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings.0`transformers.models.bridgetower.modeling_bridgetower.BridgeTowerModelOutput` or `tuple(torch.FloatTensor)`A `transformers.models.bridgetower.modeling_bridgetower.BridgeTowerModelOutput` 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 ([BridgeTowerConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerConfig)) and inputs. - **text_features** (`torch.FloatTensor` of shape `(batch_size, text_sequence_length, hidden_size)`) -- Sequence of hidden-states at the text output of the last layer of the model. - **image_features** (`torch.FloatTensor` of shape `(batch_size, image_sequence_length, hidden_size)`) -- Sequence of hidden-states at the image output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size x 2)`) -- Concatenation of last layer hidden-state of the first token of the text and image sequence (classification token), respectively, after further processing through layers used for auxiliary pretraining tasks. - **hidden_states** (`tuple[torch.FloatTensor] | None.hidden_states`, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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] | None.attentions`, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.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 [BridgeTowerModel](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerModel) 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: ```python >>> from transformers import BridgeTowerProcessor, BridgeTowerModel >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> # prepare image and text >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> text = "hello world" >>> processor = BridgeTowerProcessor.from_pretrained("BridgeTower/bridgetower-base") >>> model = BridgeTowerModel.from_pretrained("BridgeTower/bridgetower-base") >>> inputs = processor(image, text, return_tensors="pt") >>> outputs = model(**inputs) >>> outputs.keys() odict_keys(['text_features', 'image_features', 'pooler_output']) ``` **Parameters:** config ([BridgeTowerModel](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerModel)) : 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()](/docs/transformers/v5.2.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``transformers.models.bridgetower.modeling_bridgetower.BridgeTowerModelOutput` or `tuple(torch.FloatTensor)`` A `transformers.models.bridgetower.modeling_bridgetower.BridgeTowerModelOutput` 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 ([BridgeTowerConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerConfig)) and inputs. - **text_features** (`torch.FloatTensor` of shape `(batch_size, text_sequence_length, hidden_size)`) -- Sequence of hidden-states at the text output of the last layer of the model. - **image_features** (`torch.FloatTensor` of shape `(batch_size, image_sequence_length, hidden_size)`) -- Sequence of hidden-states at the image output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size x 2)`) -- Concatenation of last layer hidden-state of the first token of the text and image sequence (classification token), respectively, after further processing through layers used for auxiliary pretraining tasks. - **hidden_states** (`tuple[torch.FloatTensor] | None.hidden_states`, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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] | None.attentions`, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.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. ## BridgeTowerForContrastiveLearning[[transformers.BridgeTowerForContrastiveLearning]] #### transformers.BridgeTowerForContrastiveLearning[[transformers.BridgeTowerForContrastiveLearning]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/modeling_bridgetower.py#L1729) BridgeTower Model with a image-text contrastive head on top computing image-text contrastive loss. This model inherits from [PreTrainedModel](/docs/transformers/v5.2.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.BridgeTowerForContrastiveLearning.forwardhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/modeling_bridgetower.py#L1743[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "pixel_mask", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "image_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = True"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "return_loss", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.2.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.2.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.2.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_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?](../glossary#token-type-ids) - **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast). See [BridgeTowerImageProcessorFast.__call__()](/docs/transformers/v5.2.0/en/model_doc/fuyu#transformers.FuyuImageProcessor.__call__) for details ([BridgeTowerProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) uses [BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast) for processing images). - **pixel_mask** (`torch.LongTensor` of shape `(batch_size, height, width)`, *optional*) -- Mask to avoid performing attention on padding pixel values. Mask values selected in `[0, 1]`: - 1 for pixels that are real (i.e. **not masked**), - 0 for pixels that are padding (i.e. **masked**). [What are attention masks?](../glossary#attention-mask) - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **image_embeds** (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`, *optional*) -- Optionally, instead of passing `pixel_values`, you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `pixel_values` into patch embeddings. - **output_attentions** (`bool`, *optional*) -- Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. - **output_hidden_states** (`bool`, *optional*, defaults to `True`) -- Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. - **return_loss** (`bool`, *optional*) -- Whether or not to return the contrastive loss.0`transformers.models.bridgetower.modeling_bridgetower.BridgeTowerContrastiveOutput` or `tuple(torch.FloatTensor)`A `transformers.models.bridgetower.modeling_bridgetower.BridgeTowerContrastiveOutput` 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 ([BridgeTowerConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `return_loss` is `True`) -- Image-text contrastive loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **text_embeds** (`torch.FloatTensor)`, *optional*, returned when model is initialized with `with_projection=True`) -- The text embeddings obtained by applying the projection layer to the pooler_output. - **image_embeds** (`torch.FloatTensor)`, *optional*, returned when model is initialized with `with_projection=True`) -- The image embeddings obtained by applying the projection layer to the pooler_output. - **cross_embeds** (`torch.FloatTensor)`, *optional*, returned when model is initialized with `with_projection=True`) -- The text-image cross-modal embeddings obtained by applying the projection layer to the pooler_output. - **hidden_states** (`tuple[torch.FloatTensor] | None.hidden_states`, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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 when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. The [BridgeTowerForContrastiveLearning](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerForContrastiveLearning) 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: ```python >>> from transformers import BridgeTowerProcessor, BridgeTowerForContrastiveLearning >>> import httpx >>> from io import BytesIO >>> from PIL import Image >>> import torch >>> image_urls = [ ... "https://farm4.staticflickr.com/3395/3428278415_81c3e27f15_z.jpg", ... "http://images.cocodataset.org/val2017/000000039769.jpg", ... ] >>> texts = ["two dogs in a car", "two cats sleeping on a couch"] >>> with httpx.stream("GET", urls[0]) as response: ... image1 = Image.open(BytesIO(response.read())) >>> with httpx.stream("GET", urls[1]) as response: ... image2 = Image.open(BytesIO(response.read())) >>> images = [image1, image2] >>> processor = BridgeTowerProcessor.from_pretrained("BridgeTower/bridgetower-large-itm-mlm-itc") >>> model = BridgeTowerForContrastiveLearning.from_pretrained("BridgeTower/bridgetower-large-itm-mlm-itc") >>> inputs = processor(images, texts, padding=True, return_tensors="pt") >>> loss = model(**inputs, return_loss=True).loss >>> inputs = processor(images, texts[::-1], padding=True, return_tensors="pt") >>> loss_swapped = model(**inputs, return_loss=True).loss >>> print("Loss", round(loss.item(), 4)) Loss 0.0019 >>> print("Loss with swapped images", round(loss_swapped.item(), 4)) Loss with swapped images 2.126 ``` **Parameters:** config ([BridgeTowerForContrastiveLearning](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerForContrastiveLearning)) : 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()](/docs/transformers/v5.2.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``transformers.models.bridgetower.modeling_bridgetower.BridgeTowerContrastiveOutput` or `tuple(torch.FloatTensor)`` A `transformers.models.bridgetower.modeling_bridgetower.BridgeTowerContrastiveOutput` 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 ([BridgeTowerConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `return_loss` is `True`) -- Image-text contrastive loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **text_embeds** (`torch.FloatTensor)`, *optional*, returned when model is initialized with `with_projection=True`) -- The text embeddings obtained by applying the projection layer to the pooler_output. - **image_embeds** (`torch.FloatTensor)`, *optional*, returned when model is initialized with `with_projection=True`) -- The image embeddings obtained by applying the projection layer to the pooler_output. - **cross_embeds** (`torch.FloatTensor)`, *optional*, returned when model is initialized with `with_projection=True`) -- The text-image cross-modal embeddings obtained by applying the projection layer to the pooler_output. - **hidden_states** (`tuple[torch.FloatTensor] | None.hidden_states`, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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 when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. ## BridgeTowerForMaskedLM[[transformers.BridgeTowerForMaskedLM]] #### transformers.BridgeTowerForMaskedLM[[transformers.BridgeTowerForMaskedLM]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/modeling_bridgetower.py#L1507) BridgeTower Model with a language modeling head on top as done during pretraining. This model inherits from [PreTrainedModel](/docs/transformers/v5.2.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.BridgeTowerForMaskedLM.forwardhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/modeling_bridgetower.py#L1525[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "pixel_mask", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "image_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.2.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.2.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.2.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_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?](../glossary#token-type-ids) - **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast). See [BridgeTowerImageProcessorFast.__call__()](/docs/transformers/v5.2.0/en/model_doc/fuyu#transformers.FuyuImageProcessor.__call__) for details ([BridgeTowerProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) uses [BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast) for processing images). - **pixel_mask** (`torch.LongTensor` of shape `(batch_size, height, width)`, *optional*) -- Mask to avoid performing attention on padding pixel values. Mask values selected in `[0, 1]`: - 1 for pixels that are real (i.e. **not masked**), - 0 for pixels that are padding (i.e. **masked**). [What are attention masks?](../glossary#attention-mask) - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **image_embeds** (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`, *optional*) -- Optionally, instead of passing `pixel_values`, you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `pixel_values` into patch embeddings. - **output_attentions** (`bool`, *optional*) -- Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. - **output_hidden_states** (`bool`, *optional*) -- Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. - **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`0[transformers.modeling_outputs.MaskedLMOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.MaskedLMOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) 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 ([BridgeTowerConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Masked language modeling (MLM) loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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 when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.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 [BridgeTowerForMaskedLM](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerForMaskedLM) 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: ```python >>> from transformers import BridgeTowerProcessor, BridgeTowerForMaskedLM >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> url = "http://images.cocodataset.org/val2017/000000360943.jpg" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())).convert("RGB") >>> text = "a looking out of the window" >>> processor = BridgeTowerProcessor.from_pretrained("BridgeTower/bridgetower-base-itm-mlm") >>> model = BridgeTowerForMaskedLM.from_pretrained("BridgeTower/bridgetower-base-itm-mlm") >>> # prepare inputs >>> encoding = processor(image, text, return_tensors="pt") >>> # forward pass >>> outputs = model(**encoding) >>> results = processor.decode(outputs.logits.argmax(dim=-1).squeeze(0).tolist()) >>> print(results) .a cat looking out of the window. ``` **Parameters:** config ([BridgeTowerForMaskedLM](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerForMaskedLM)) : 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()](/docs/transformers/v5.2.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[transformers.modeling_outputs.MaskedLMOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)`` A [transformers.modeling_outputs.MaskedLMOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) 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 ([BridgeTowerConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Masked language modeling (MLM) loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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 when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.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. ## BridgeTowerForImageAndTextRetrieval[[transformers.BridgeTowerForImageAndTextRetrieval]] #### transformers.BridgeTowerForImageAndTextRetrieval[[transformers.BridgeTowerForImageAndTextRetrieval]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/modeling_bridgetower.py#L1617) BridgeTower Model transformer with a classifier head on top (a linear layer on top of the final hidden state of the [CLS] token) for image-to-text matching. This model inherits from [PreTrainedModel](/docs/transformers/v5.2.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.BridgeTowerForImageAndTextRetrieval.forwardhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/bridgetower/modeling_bridgetower.py#L1628[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "pixel_mask", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "image_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.2.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.2.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.2.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_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?](../glossary#attention-mask) - **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_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?](../glossary#token-type-ids) - **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast). See [BridgeTowerImageProcessorFast.__call__()](/docs/transformers/v5.2.0/en/model_doc/fuyu#transformers.FuyuImageProcessor.__call__) for details ([BridgeTowerProcessor](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) uses [BridgeTowerImageProcessorFast](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerImageProcessorFast) for processing images). - **pixel_mask** (`torch.LongTensor` of shape `(batch_size, height, width)`, *optional*) -- Mask to avoid performing attention on padding pixel values. Mask values selected in `[0, 1]`: - 1 for pixels that are real (i.e. **not masked**), - 0 for pixels that are padding (i.e. **masked**). [What are attention masks?](../glossary#attention-mask) - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **image_embeds** (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`, *optional*) -- Optionally, instead of passing `pixel_values`, you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `pixel_values` into patch embeddings. - **output_attentions** (`bool`, *optional*) -- Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. - **output_hidden_states** (`bool`, *optional*) -- Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. - **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.0[transformers.modeling_outputs.SequenceClassifierOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.SequenceClassifierOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) 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 ([BridgeTowerConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Classification (or regression if config.num_labels==1) loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`) -- Classification (or regression if config.num_labels==1) scores (before SoftMax). - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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 when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.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 [BridgeTowerForImageAndTextRetrieval](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerForImageAndTextRetrieval) 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: ```python >>> from transformers import BridgeTowerProcessor, BridgeTowerForImageAndTextRetrieval >>> import httpx >>> from io import BytesIO >>> from PIL import Image >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> texts = ["An image of two cats chilling on a couch", "A football player scoring a goal"] >>> processor = BridgeTowerProcessor.from_pretrained("BridgeTower/bridgetower-base-itm-mlm") >>> model = BridgeTowerForImageAndTextRetrieval.from_pretrained("BridgeTower/bridgetower-base-itm-mlm") >>> # forward pass >>> scores = dict() >>> for text in texts: ... # prepare inputs ... encoding = processor(image, text, return_tensors="pt") ... outputs = model(**encoding) ... scores[text] = outputs.logits[0, 1].item() ``` **Parameters:** config ([BridgeTowerForImageAndTextRetrieval](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerForImageAndTextRetrieval)) : 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()](/docs/transformers/v5.2.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[transformers.modeling_outputs.SequenceClassifierOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`` A [transformers.modeling_outputs.SequenceClassifierOutput](/docs/transformers/v5.2.0/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) 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 ([BridgeTowerConfig](/docs/transformers/v5.2.0/en/model_doc/bridgetower#transformers.BridgeTowerConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Classification (or regression if config.num_labels==1) loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`) -- Classification (or regression if config.num_labels==1) scores (before SoftMax). - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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 when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.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.