a hc8@sdZddlmZddlmZddlmZmZmZerLddl m Z ddl m Z ddl mZdd lmZdd l mZeeZGd d d eZGd ddeZGdddeZGdddeZgdZdS)zOWL-ViT model configuration OrderedDict)Mapping) TYPE_CHECKINGAnyOptional)ProcessorMixin) TensorType)PretrainedConfig) OnnxConfig)loggingcs*eZdZdZdZdZdfdd 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`tjf| | |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$r%r&r'r(r)r*r+r,rrrkwargs __class__k/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/owlvit/configuration_owlvit.pyr!aszOwlViTTextConfig.__init__)rrrrrrrrrrrrrr__name__ __module__ __qualname____doc__ model_typeZbase_config_keyr! __classcell__r1r1r/r2r"s$;rc s*eZdZdZdZdZdfdd 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^tjfi| ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ dS)N)r r!r#r$r%r& num_channels image_size patch_sizer(r)r*r+r,)r-r#r$r%r&r?r@rAr(r)r*r+r,r.r/r1r2r!szOwlViTVisionConfig.__init__) r<r=rrrr<r>rrrrrr3r1r1r/r2r:s 4r:csDeZdZdZdZeedZd fdd Ze e e dd 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 sztjfi||dur(i}td|dur>i}tdtfi||_tfi||_||_||_ ||_ d|_ dS)NzKtext_config is None. Initializing the OwlViTTextConfig with default values.zOvision_config is None. initializing the OwlViTVisionConfig with default values.r) r r!loggerinforrr:r;projection_dimlogit_scale_init_value return_dictr,)r-rr;rFrGrHr.r/r1r2r!s   zOwlViTConfig.__init__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;r.Z config_dictr1r1r2from_text_vision_configss z%OwlViTConfig.from_text_vision_configs)NNrrCT) r4r5r6r7r8rr:Z sub_configsr! classmethoddictrKr9r1r1r/r2rBs rBcseZdZeeeeeeffdddZeeeeeeffdddZee dddZ dd eee d eee fd fd d Z eedddZZS)OwlViTOnnxConfig)returncCs0tddddfdddddd fd dddfgS) NZ input_idsbatchsequence)rZ pixel_valuesr?heightwidth)rrRrZattention_maskrr-r1r1r2inputs#s   zOwlViTOnnxConfig.inputscCs0tdddifdddifdddifdddifgS)NZlogits_per_imagerrPZlogits_per_textZ text_embedsZ image_embedsrrVr1r1r2outputs-s    zOwlViTOnnxConfig.outputscCsdS)Ng-C6?r1rVr1r1r2atol_for_validation8sz$OwlViTOnnxConfig.atol_for_validationNr r ) processor batch_size seq_length frameworkrOcs6tj|j|||d}tj|j||d}i||S)N)r\r]r^)r\r^)r generate_dummy_inputs tokenizerZimage_processor)r-r[r\r]r^Ztext_input_dictZimage_input_dictr/r1r2r_<s z&OwlViTOnnxConfig.generate_dummy_inputscCsdS)Nr1rVr1r1r2default_onnx_opsetKsz#OwlViTOnnxConfig.default_onnx_opset)rZrZN)r4r5r6propertyrstrintrWrXfloatrYrrr_rbr9r1r1r/r2rN"s$   rN)rBrNrr:N)r7 collectionsrcollections.abcrtypingrrrZprocessing_utilsr utilsr Zconfiguration_utilsr Zonnxr r Z get_loggerr4rDrr:rBrN__all__r1r1r1r2s        `XH.