o ZhK@sdZddlmZddlmZmZmZmZer"ddlm Z ddl m Z ddl m Z ddlmZdd l mZeeZGd d d e ZGd d d e ZGddde ZGdddeZgdZdS)zCLIP model configuration OrderedDict) TYPE_CHECKINGAnyMappingOptional)ProcessorMixin) TensorType)PretrainedConfig) OnnxConfig)loggingcsHeZdZdZdZdZ          dfdd ZZS)CLIPTextConfiga This is the configuration class to store the configuration of a [`CLIPTextModel`]. It is used to instantiate a CLIP 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 text encoder of the CLIP [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-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 CLIP text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`CLIPModel`]. 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. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. 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 77): 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 1): Padding token id. bos_token_id (`int`, *optional*, defaults to 49406): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 49407): End of stream token id. Example: ```python >>> from transformers import CLIPTextConfig, CLIPTextModel >>> # Initializing a CLIPTextConfig with openai/clip-vit-base-patch32 style configuration >>> configuration = CLIPTextConfig() >>> # Initializing a CLIPTextModel (with random weights) from the openai/clip-vit-base-patch32 style configuration >>> model = CLIPTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zclip_text_model text_config M quick_geluh㈵>{Gz??c sftjd| ||d|||_||_||_||_||_||_||_| |_ ||_ | |_ | |_ | |_ dS)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_size hidden_sizeintermediate_sizeprojection_dimnum_hidden_layersnum_attention_headsmax_position_embeddingslayer_norm_eps hidden_actinitializer_rangeinitializer_factorattention_dropout)selfr$r%r&r'r(r)r*r,r+r/r-r.rrr kwargs __class__r!Z/var/www/auris/lib/python3.10/site-packages/transformers/models/clip/configuration_clip.pyr#as zCLIPTextConfig.__init__)rrrrrrrrrrrrrrr__name__ __module__ __qualname____doc__ model_typeZbase_config_keyr# __classcell__r!r!r2r4r!s(<rcsDeZdZdZdZdZ        dfdd ZZS)CLIPVisionConfiga This is the configuration class to store the configuration of a [`CLIPVisionModel`]. It is used to instantiate a CLIP vision 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 vision encoder of the CLIP [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-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. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. 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): The number of input channels. image_size (`int`, *optional*, defaults to 224): 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 CLIPVisionConfig, CLIPVisionModel >>> # Initializing a CLIPVisionConfig with openai/clip-vit-base-patch32 style configuration >>> configuration = CLIPVisionConfig() >>> # Initializing a CLIPVisionModel (with random weights) from the openai/clip-vit-base-patch32 style configuration >>> model = CLIPVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zclip_vision_model vision_config rrr rrrrrc sdtjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_dS)Nr!)r"r#r%r&r'r(r) num_channels patch_size image_sizer-r.r/r+r,)r0r%r&r'r(r)rBrDrCr,r+r/r-r.r1r2r!r4r#s zCLIPVisionConfig.__init__) r>r?rrrrr@rArrrrrr5r!r!r2r4r<s$6r<csHeZdZdZdZeedZ d fdd Ze d ed efd d Z Z S) CLIPConfigaN [`CLIPConfig`] is the configuration class to store the configuration of a [`CLIPModel`]. It is used to instantiate a CLIP 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 CLIP [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-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 [`CLIPTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`CLIPVisionConfig`]. 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 CLIP implementation. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import CLIPConfig, CLIPModel >>> # Initializing a CLIPConfig with openai/clip-vit-base-patch32 style configuration >>> configuration = CLIPConfig() >>> # Initializing a CLIPModel (with random weights) from the openai/clip-vit-base-patch32 style configuration >>> model = CLIPModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a CLIPConfig from a CLIPTextConfig and a CLIPVisionConfig >>> from transformers import CLIPTextConfig, CLIPVisionConfig >>> # Initializing a CLIPText and CLIPVision configuration >>> config_text = CLIPTextConfig() >>> config_vision = CLIPVisionConfig() >>> config = CLIPConfig.from_text_vision_configs(config_text, config_vision) ```Zcliprr=Nr/L F@c  s|dd}|dd}tjdi||dur]|duri}tdi|}|D]+\} } | |vrW| || krW| dvrW| |vrLd| d| d} nd| d} t| q,|||dur|durgi}t di|} d | vrd d | d D| d <| D]+\} } | |vr| || kr| dvr| |vrd| d | d} nd | d} t| q|| |duri}td|duri}tdtdi||_ t di||_ ||_ ||_ d|_dS)Ntext_config_dictvision_config_dict)Ztransformers_version`zp` is found in both `text_config_dict` and `text_config` but with different values. The value `text_config_dict["z"]` will be used instead.zj`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["z"]` will be overridden.Zid2labelcSsi|] \}}t||qSr!)str).0keyvaluer!r!r4 Dsz'CLIPConfig.__init__..zv` is found in both `vision_config_dict` and `vision_config` but with different values. The value `vision_config_dict["zp`vision_config_dict` is provided which will be used to initialize `CLIPVisionConfig`. The value `vision_config["zO`text_config` is `None`. Initializing the `CLIPTextConfig` with default values.zS`vision_config` is `None`. initializing the `CLIPVisionConfig` with default values.rr!)popr"r#rto_dictitemsloggerinfoupdater<rr=r'logit_scale_init_valuer.) r0rr=r'rVr1rHrIZ_text_config_dictrMrNmessageZ_vision_config_dictr2r!r4r#sl           zCLIPConfig.__init__rr=cKs|d||d|S)z Instantiate a [`CLIPConfig`] (or a derived class) from clip text model configuration and clip vision model configuration. Returns: [`CLIPConfig`]: An instance of a configuration object rFNr!)rQ)clsrr=r1r!r!r4from_text_vision_configsks z#CLIPConfig.from_text_vision_configs)NNrrG) r6r7r8r9r:rr<Z sub_configsr# classmethodrYr;r!r!r2r4rEs- XrEc seZdZedeeeeefffddZedeeeeefffddZede fddZ   dd d d ed ede ddeee ff fdd Z edefddZZS)CLIPOnnxConfigreturncCs0tddddfdddddd fd dddfgS) NZ input_idsbatchsequence)rrZ pixel_valuesrBheightwidth)rrrZattention_maskrr0r!r!r4inputsys   zCLIPOnnxConfig.inputscCs0tdddifdddifdddifdddifgS)NZlogits_per_imagerr]Zlogits_per_textZ text_embedsZ image_embedsrrbr!r!r4outputss    zCLIPOnnxConfig.outputscCdS)Ng-C6?r!rbr!r!r4atol_for_validationz"CLIPOnnxConfig.atol_for_validationN processorr batch_size seq_length frameworkr cs6tj|j|||d}tj|j||d}i||S)N)rjrkrl)rjrl)r"generate_dummy_inputsZ tokenizerZimage_processor)r0rirjrkrlZtext_input_dictZimage_input_dictr2r!r4rms  z$CLIPOnnxConfig.generate_dummy_inputscCre)Nr!rbr!r!r4default_onnx_opsetrgz!CLIPOnnxConfig.default_onnx_opset)rhrhN)r6r7r8propertyrrKintrcrdfloatrfrrrmror;r!r!r2r4r[xs.    r[)rEr[rr<N)r9 collectionsrtypingrrrrZprocessing_utilsr utilsr Zconfiguration_utilsr Zonnxr r Z get_loggerr6rSrr<rEr[__all__r!r!r!r4s        e\ .