sgvJdZddlmZddlmZmZmZmZddlm Z ddl m Z ddl m Z er ddlmZdd l mZe j"eZGd d e ZGd d e ZGdde ZGdde Zy)zGroupViT model configuration OrderedDict) TYPE_CHECKINGAnyMappingOptional)PretrainedConfig) OnnxConfig)logging)ProcessorMixin) TensorTypecJeZdZdZdZdZ dfd ZxZS)GroupViTTextConfiga> This is the configuration class to store the configuration of a [`GroupViTTextModel`]. It is used to instantiate an GroupViT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the GroupViT [nvidia/groupvit-gcc-yfcc](https://huggingface.co/nvidia/groupvit-gcc-yfcc) 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 GroupViT text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`GroupViTModel`]. hidden_size (`int`, *optional*, defaults to 256): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 1024): 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 4): 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-5): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. dropout (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. 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 GroupViTTextConfig, GroupViTTextModel >>> # Initializing a GroupViTTextModel with nvidia/groupvit-gcc-yfcc style configuration >>> configuration = GroupViTTextConfig() >>> model = GroupViTTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```groupvit_text_model text_configc t|d| ||d|||_||_||_| |_||_||_||_||_ ||_ | |_ | |_ | |_ y)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_size hidden_sizeintermediate_sizedropoutnum_hidden_layersnum_attention_headsmax_position_embeddingslayer_norm_eps hidden_actinitializer_rangeinitializer_factorattention_dropout)selfrrrrrr r"r!rr%r#r$rrrkwargs __class__s f/var/www/html/venv/lib/python3.12/site-packages/transformers/models/groupvit/configuration_groupvit.pyrzGroupViTTextConfig.__init__Zs}& sl\hslrs$&!2 !2#6 '>$,$!2"4!2)ii M quick_geluh㈵>r1{Gz??ii__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__r(s@r)rr!sN3 j'J#O "! 3 3r*rc`eZdZdZdZdZddgddgdgd d d d d dddddddddgffd ZxZS)GroupViTVisionConfiga@ This is the configuration class to store the configuration of a [`GroupViTVisionModel`]. It is used to instantiate an GroupViT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the GroupViT [nvidia/groupvit-gcc-yfcc](https://huggingface.co/nvidia/groupvit-gcc-yfcc) 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 384): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 1536): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. depths (`List[int]`, *optional*, defaults to [6, 3, 3]): The number of layers in each encoder block. num_group_tokens (`List[int]`, *optional*, defaults to [64, 8, 0]): The number of group tokens for each stage. num_output_groups (`List[int]`, *optional*, defaults to [64, 8, 8]): The number of output groups for each stage, 0 means no group. num_attention_heads (`int`, *optional*, defaults to 6): Number of attention heads for each attention layer in the Transformer encoder. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"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-5): The epsilon used by the layer normalization layers. dropout (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. 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 GroupViTVisionConfig, GroupViTVisionModel >>> # Initializing a GroupViTVisionModel with nvidia/groupvit-gcc-yfcc style configuration >>> configuration = GroupViTVisionConfig() >>> model = GroupViTVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```groupvit_vision_model vision_configii)r r r,)@r)rCrDrDrBr gelur0r1r2r3g?r-c t|di|||_||_||_|t |k7r$t jd|dt |||_||_ ||_ ||_ ||_ | |_ | |_| |_| |_| |_||_||_||_||_||_y)Nz&Manually setting num_hidden_layers to z1, but we expect num_hidden_layers = sum(depth) = r)rrrrdepthssumloggerwarningrnum_group_tokensnum_output_groupsr image_size patch_size num_channelsr"r!rr%r#r$ assign_epsassign_mlp_ratio)r&rrrIrrMrNrrOrPrQr"r!rr%r#r$rRrSr'r(s r)rzGroupViTVisionConfig.__init__s, "6"&!2 F + NN89J8KL!!$V / "3 0!2#6 $$($, !2!2"4$ 0r*r5r=s@r)r?r?}s[5 n)J%O#$q'.1.1r*r?cVeZdZdZdZeedZ dfd Ze dedefdZ xZ S) GroupViTConfiga [`GroupViTConfig`] is the configuration class to store the configuration of a [`GroupViTModel`]. It is used to instantiate a GroupViT 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 GroupViT [nvidia/groupvit-gcc-yfcc](https://huggingface.co/nvidia/groupvit-gcc-yfcc) 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 [`GroupViTTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`GroupViTVisionConfig`]. projection_dim (`int`, *optional*, defaults to 256): Dimensionality of text and vision projection layers. projection_intermediate_dim (`int`, *optional*, defaults to 4096): Dimensionality of intermediate layer 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 GroupViT implementation. kwargs (*optional*): Dictionary of keyword arguments. groupvitrrAc |jdd}|jdd}t|di|||i}tdi|j } | j D]A\} } | |vs | || k7s| dvs| |vr d| d| d} nd| d} t j| C|j| ||i}tdi|j } d | vr3| d j D cic]\} } t| | c} } | d <| j D]A\} } | |vs | || k7s| dvs| |vr d| d | d} nd | d} t j| C|j| |i}t jd |i}t jd tdi||_ tdi||_ ||_ ||_||_d|_d|_d|_ycc} } w)Ntext_config_dictvision_config_dict)transformers_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.zn`text_config_dict` is provided which will be used to initialize `GroupViTTextConfig`. The value `text_config["z"]` will be overridden.id2labelzv` is found in both `vision_config_dict` and `vision_config` but with different values. The value `vision_config_dict["zt`vision_config_dict` is provided which will be used to initialize `GroupViTVisionConfig`. The value `vision_config["zS`text_config` is `None`. Initializing the `GroupViTTextConfig` with default values.zW`vision_config` is `None`. initializing the `GroupViTVisionConfig` with default values.r2r3Fr)poprrrto_dictitemsrKinfoupdater?strrrAprojection_dimprojection_intermediate_dimlogit_scale_init_valuer#r$output_segmentation)r&rrArdrerfr'rYrZ_text_config_dictkeyvaluemessage_vision_config_dictr(s r)rzGroupViTConfig.__init__s"::&8$?#ZZ(UW KK( )"  !4 5  K KKm n  M KKq r-< <1BMB,+F(&<#!%"%#( Q3s2G1rrAc P|d|j|jd|S)z Instantiate a [`GroupViTConfig`] (or a derived class) from groupvit text model configuration and groupvit vision model configuration. Returns: [`GroupViTConfig`]: An instance of a configuration object rWr)r_)clsrrAr's r)from_text_vision_configsz'GroupViTConfig.from_text_vision_configsgs,f{224MDYDYD[f_effr*)NNr+ig/L F@) r6r7r8r9r:rr? sub_configsr classmethodror<r=s@r)rUrUsZ2J"4G[\K$(% _)B g3E gVj g gr*rUc eZdZedeeeeefffdZedeeeeefffdZede fdZ d dddeded e d deee ff fd Z edefd ZxZS)GroupViTOnnxConfigreturnc @tddddfdddddd fd dddfgS) N input_idsbatchsequence)rr4 pixel_valuesrQheightwidth)rr4r attention_maskrr&s r)inputszGroupViTOnnxConfig.inputsus@'j9:WHQX!YZ!w:#>?   r*c@tdddifdddifdddifdddifgS)Nlogits_per_imagerrwlogits_per_text text_embeds image_embedsrr~s r)outputszGroupViTOnnxConfig.outputssD#a\2"QL1G -!W.    r*cy)Ng-C6?rr~s r)atol_for_validationz&GroupViTOnnxConfig.atol_for_validationsr* processorr batch_size seq_length frameworkrct||j|||}t||j||}i||S)N)rrr)rr)rgenerate_dummy_inputs tokenizerimage_processor)r&rrrrtext_input_dictimage_input_dictr(s r)rz(GroupViTOnnxConfig.generate_dummy_inputss` '7   J:Yb8 !78  % %* 9 7/6%566r*cy)Nrr~s r)default_onnx_opsetz%GroupViTOnnxConfig.default_onnx_opsetsr*)rN)r6r7r8propertyrrcintrrfloatrrrrrr<r=s@r)rsrsts  WS#X%6 67   gc3h&7!78  U ,0 7# 7 7 7 L) 7 c  7Cr*rsN)r9 collectionsrtypingrrrrconfiguration_utilsr onnxr utilsr processing_utilsr r get_loggerr6rKrr?rUrsrr*r)rsy##8832#   H %Y3)Y3xi1+i1XHg%HgV++r*