o ZhN8@sdZddlmZddlmZmZmZmZmZer$ddl m Z ddl m Z ddl mZddlmZdd l mZeeZGd d d eZGd d d eZGdddeZGdddeZgdZdS)zOWL-ViT model configuration OrderedDict) TYPE_CHECKINGAnyDictMappingOptional)ProcessorMixin) TensorType)PretrainedConfig) OnnxConfig)loggingcsFeZdZdZdZdZ         dfdd ZZS)OwlViTTextConfiga This is the configuration class to store the configuration of an [`OwlViTTextModel`]. It is used to instantiate an OwlViT text encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the OwlViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 49408): Vocabulary size of the OWL-ViT text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`OwlViTTextModel`]. hidden_size (`int`, *optional*, defaults to 512): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. max_position_embeddings (`int`, *optional*, defaults to 16): 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). hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): 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. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). pad_token_id (`int`, *optional*, defaults to 0): The id of the padding token in the input sequences. bos_token_id (`int`, *optional*, defaults to 49406): The id of the beginning-of-sequence token in the input sequences. eos_token_id (`int`, *optional*, defaults to 49407): The id of the end-of-sequence token in the input sequences. Example: ```python >>> from transformers import OwlViTTextConfig, OwlViTTextModel >>> # Initializing a OwlViTTextModel with google/owlvit-base-patch32 style configuration >>> configuration = OwlViTTextConfig() >>> # Initializing a OwlViTTextConfig from the google/owlvit-base-patch32 style configuration >>> model = OwlViTTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zowlvit_text_model text_config  quick_geluh㈵>{Gz??rc s`tjd| | |d|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ dS)N) pad_token_id bos_token_id eos_token_id) super__init__ vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsmax_position_embeddings hidden_actlayer_norm_epsattention_dropoutinitializer_rangeinitializer_factor)selfr$r%r&r'r(r)r*r+r,r-r.rrr kwargs __class__r!^/var/www/auris/lib/python3.10/site-packages/transformers/models/owlvit/configuration_owlvit.pyr#`s zOwlViTTextConfig.__init__)rrrrrrrrrrrrrr__name__ __module__ __qualname____doc__ model_typeZbase_config_keyr# __classcell__r!r!r1r3r!s&;rcsBeZdZdZdZdZ        dfdd ZZS)OwlViTVisionConfigah This is the configuration class to store the configuration of an [`OwlViTVisionModel`]. It is used to instantiate an OWL-ViT image encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the OWL-ViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. 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. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input images. image_size (`int`, *optional*, defaults to 768): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 32): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): 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. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). Example: ```python >>> from transformers import OwlViTVisionConfig, OwlViTVisionModel >>> # Initializing a OwlViTVisionModel with google/owlvit-base-patch32 style configuration >>> configuration = OwlViTVisionConfig() >>> # Initializing a OwlViTVisionModel model from the google/owlvit-base-patch32 style configuration >>> model = OwlViTVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zowlvit_vision_model vision_config rr rrrrrc  s^tjdi| ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ dS)Nr!)r"r#r%r&r'r( num_channels image_size patch_sizer*r+r,r-r.)r/r%r&r'r(r@rArBr*r+r,r-r.r0r1r!r3r#s zOwlViTVisionConfig.__init__) r=r>rrr r=r?rrrrrr4r!r!r1r3r;s"4r;csPeZdZdZdZeedZ     dfdd Ze d e d e fd d Z Z S) OwlViTConfiga [`OwlViTConfig`] is the configuration class to store the configuration of an [`OwlViTModel`]. It is used to instantiate an OWL-ViT model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the OWL-ViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`OwlViTTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`OwlViTVisionConfig`]. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The initial value of the *logit_scale* parameter. Default is used as per the original OWL-ViT implementation. return_dict (`bool`, *optional*, defaults to `True`): Whether or not the model should return a dictionary. If `False`, returns a tuple. kwargs (*optional*): Dictionary of keyword arguments. Zowlvit)rr<Nr/L F@Tc sztjdi||duri}td|duri}tdtdi||_tdi||_||_||_ ||_ d|_ dS)NzKtext_config is None. Initializing the OwlViTTextConfig with default values.zOvision_config is None. initializing the OwlViTVisionConfig with default values.rr!) r"r#loggerinforrr;r<projection_dimlogit_scale_init_value return_dictr.)r/rr<rGrHrIr0r1r!r3r#s    zOwlViTConfig.__init__rr<cKs&i}||d<||d<|j|fi|S)z Instantiate a [`OwlViTConfig`] (or a derived class) from owlvit text model configuration and owlvit vision model configuration. Returns: [`OwlViTConfig`]: An instance of a configuration object rr<) from_dict)clsrr<r0Z config_dictr!r!r3from_text_vision_configss z%OwlViTConfig.from_text_vision_configs)NNrrDT) r5r6r7r8r9rr;Z sub_configsr# classmethodrrLr:r!r!r1r3rCs rCc seZdZedeeeeefffddZedeeeeefffddZede fddZ   dd d d ed ede ddeee ff fdd Z edefddZZS)OwlViTOnnxConfigreturncCs0tddddfdddddd fd dddfgS) NZ input_idsbatchsequence)rZ pixel_valuesr@heightwidth)rrRr Zattention_maskrr/r!r!r3inputs"s   zOwlViTOnnxConfig.inputscCs0tdddifdddifdddifdddifgS)NZlogits_per_imagerrPZlogits_per_textZ text_embedsZ image_embedsrrVr!r!r3outputs,s    zOwlViTOnnxConfig.outputscCdS)Ng-C6?r!rVr!r!r3atol_for_validation7z$OwlViTOnnxConfig.atol_for_validationN processorr batch_size seq_length frameworkr cs6tj|j|||d}tj|j||d}i||S)N)r^r_r`)r^r`)r"generate_dummy_inputsZ tokenizerZimage_processor)r/r]r^r_r`Ztext_input_dictZimage_input_dictr1r!r3ra;s  z&OwlViTOnnxConfig.generate_dummy_inputscCrY)Nr!rVr!r!r3default_onnx_opsetJr[z#OwlViTOnnxConfig.default_onnx_opset)r\r\N)r5r6r7propertyrstrintrWrXfloatrZrrrarcr:r!r!r1r3rN!s.    rN)rCrNrr;N)r8 collectionsrtypingrrrrrZprocessing_utilsr utilsr Zconfiguration_utilsr Zonnxr rZ get_loggerr5rErr;rCrN__all__r!r!r!r3s       `XH .