o hB@sdZddlZddlmZddlmZmZmZmZm Z m Z er*ddl m Z ddl mZddlmZdd lmZdd l mZeeZd d d dZGdddeZGdddeZGdddeZGdddeZdS)z OWL-ViT model configurationN OrderedDict) TYPE_CHECKINGAnyDictMappingOptionalUnion)ProcessorMixin) TensorType)PretrainedConfig) OnnxConfig)loggingzJhttps://huggingface.co/google/owlvit-base-patch32/resolve/main/config.jsonzJhttps://huggingface.co/google/owlvit-base-patch16/resolve/main/config.jsonzKhttps://huggingface.co/google/owlvit-large-patch14/resolve/main/config.json)zgoogle/owlvit-base-patch32zgoogle/owlvit-base-patch16zgoogle/owlvit-large-patch14csbeZdZdZdZ         dfdd Zedeee j fddfddZ Z S)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 ```owlvit_text_model  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/rr r!kwargs __class__r"e/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/owlvit/configuration_owlvit.pyr$fs zOwlViTTextConfig.__init__pretrained_model_name_or_pathreturnr cK|||j|fi|\}}|ddkr|d}d|vr:t|dr:|d|jkr:td|dd|jd|j|fi|S)N model_typeowlvit text_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr8loggerwarning from_dictclsr5r1 config_dictr"r"r4from_pretrained   z OwlViTTextConfig.from_pretrained)rrrrrrrrrrrrrr __name__ __module__ __qualname____doc__r8r$ classmethodr strosPathLikerI __classcell__r"r"r2r4r(s(; &rcs^eZdZdZdZ         dfd d Zedeee j fddfddZ Z S)OwlViTVisionConfigai 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 ```owlvit_vision_model rr rrrrrc  s^tjdi| ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ dS)Nr")r#r$r&r'r(r) num_channels image_size patch_sizer+r,r-r.r/)r0r&r'r(r)rZr[r\r+r,r-r.r/r1r2r"r4r$s zOwlViTVisionConfig.__init__r5r6r cKr7)Nr8r9 vision_configr;r<r=r>rFr"r"r4rIrJz"OwlViTVisionConfig.from_pretrained) rWrXrrr rWrYrrrrrrKr"r"r2r4rUs$4&rUcsfeZdZdZdZ     dfdd Zed eee j fd d fd d Z ede de fddZ ZS) OwlViTConfiga [`OwlViTConfig`] is the configuration class to store the configuration of an [`OwlViTModel`]. It is used to instantiate an OWL-ViT model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the OWL-ViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`OwlViTTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`OwlViTVisionConfig`]. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The inital value of the *logit_scale* parameter. Default is used as per the original OWL-ViT implementation. return_dict (`bool`, *optional*, defaults to `True`): Whether or not the model should return a dictionary. If `False`, returns a tuple. kwargs (*optional*): Dictionary of keyword arguments. r9Nr/L F@Tc sztjdi||duri}td|duri}tdtdi||_tdi||_||_||_ ||_ d|_ dS)NzKtext_config is None. Initializing the OwlViTTextConfig with default values.zOvision_config is None. initializing the OwlViTVisionConfig with default values.rr") r#r$rCinforr:rUr]projection_dimlogit_scale_init_value return_dictr/)r0r:r]rarbrcr1r2r"r4r$s    zOwlViTConfig.__init__r5r6r cKsp|||j|fi|\}}d|vr/t|dr/|d|jkr/td|dd|jd|j|fi|S)Nr8r;r<r=)r?r@rBr8rCrDrErFr"r"r4rI9s   zOwlViTConfig.from_pretrainedr:r]cKs&i}||d<||d<|j|fi|S)z Instantiate a [`OwlViTConfig`] (or a derived class) from owlvit text model configuration and owlvit vision model configuration. Returns: [`OwlViTConfig`]: An instance of a configuration object r:r])rE)rGr:r]r1rHr"r"r4from_text_vision_configsGs z%OwlViTConfig.from_text_vision_configs)NNrr_T)rLrMrNrOr8r$rPr rQrRrSrIrrdrTr"r"r2r4r^s r^c seZdZedeeeeefffddZedeeeeefffddZede fddZ   dd d d ed ede ddeee ff fdd Z edefddZZS)OwlViTOnnxConfigr6cCs0tddddfdddddd fd dddfgS) N input_idsbatchsequence)r pixel_valuesrZheightwidth)rrir attention_maskrr0r"r"r4inputsXs   zOwlViTOnnxConfig.inputscCs0tdddifdddifdddifdddifgS)Nlogits_per_imagerrglogits_per_text text_embeds image_embedsrror"r"r4outputsbs    zOwlViTOnnxConfig.outputscCdS)Ng-C6?r"ror"r"r4atol_for_validationmz$OwlViTOnnxConfig.atol_for_validationN processorr batch_size seq_length frameworkr cs6tj|j|||d}tj|j||d}i||S)N)r{r|r})r{r})r#generate_dummy_inputs tokenizerimage_processor)r0rzr{r|r}text_input_dictimage_input_dictr2r"r4r~qs  z&OwlViTOnnxConfig.generate_dummy_inputscCrv)Nr"ror"r"r4default_onnx_opsetrxz#OwlViTOnnxConfig.default_onnx_opset)ryryN)rLrMrNpropertyrrQintrprufloatrwrrr~rrTr"r"r2r4reWs.    re)rOrR collectionsrtypingrrrrrr processing_utilsr utilsr configuration_utilsr onnxrr get_loggerrLrC$OWLVIT_PRETRAINED_CONFIG_ARCHIVE_MAPrrUr^rer"r"r"r4s&        qiU