o ¾e¦i^0ã@sbdZddlmZddlmZe e¡ZGdd„deƒZGdd„deƒZ Gdd „d eƒZ gd ¢Z d S) zOWL-ViT model configurationé)ÚPreTrainedConfig)ÚloggingcsFeZdZdZdZdZ         d‡fdd„ Z‡ZS)ÚOwlViTTextConfiga‡ 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 ```Úowlvit_text_modelÚ text_configéÁééé ééÚ quick_geluçñh㈵øä>çç{®Gáz”?çð?ééþÀéÿÀc sjtƒjdi|¤Ž| |_| |_||_||_||_||_||_||_ ||_ ||_ ||_ | |_ | |_| |_dS©N©)ÚsuperÚ__init__Ú pad_token_idÚ bos_token_idÚ eos_token_idÚ vocab_sizeÚ hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚmax_position_embeddingsÚ hidden_actÚlayer_norm_epsÚattention_dropoutÚinitializer_rangeÚinitializer_factor)Úselfrrrrr r!r"r#r$r%r&rrrÚkwargs©Ú __class__rúm/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/owlvit/configuration_owlvit.pyrVs zOwlViTTextConfig.__init__)rrr r r r r rrrrrrr©Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚbase_config_keyrÚ __classcell__rrr)r+rs&;ñrcsBeZdZdZdZdZ        d‡fdd„ Z‡ZS)ÚOwlViTVisionConfigah 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 ```Úowlvit_vision_modelÚ vision_configéé r ré r rrrrc  s^tƒjdi| ¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ dSr)rrrrrr Ú num_channelsÚ image_sizeÚ patch_sizer"r#r$r%r&)r'rrrr r:r;r<r"r#r$r%r&r(r)rr+r²s zOwlViTVisionConfig.__init__) r7r8r r rr7r9r rrrrr,rrr)r+r4zs"4ór4cs:eZdZdZdZeedœZ     d ‡fdd „ Z‡Z S) Ú OwlViTConfiga½ [`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. Úowlvit)rr6Nrçƒ/L¦ F@Tc sž|dur tƒ}t d¡n t|tƒrtdi|¤Ž}|dur&tƒ}t d¡n t|tƒr2tdi|¤Ž}||_||_||_||_ ||_ d|_ t ƒj di|¤ŽdS)NzQ`text_config` is `None`. initializing the `OwlViTTextConfig` with default values.zU`vision_config` is `None`. initializing the `OwlViTVisionConfig` with default values.rr)rÚloggerÚinfoÚ isinstanceÚdictr4rr6Úprojection_dimÚlogit_scale_init_valueÚ return_dictr&rr)r'rr6rDrErFr(r)rr+rïs"     zOwlViTConfig.__init__)NNrr?T) r-r.r/r0r1rr4Ú sub_configsrr3rrr)r+r=Òs úr=)r=rr4N) r0Úconfiguration_utilsrÚutilsrÚ get_loggerr-r@rr4r=Ú__all__rrrr+Ús   cX <