o ZŽh™Kã@sbdZddlmZddlmZe e¡ZGdd„deƒZGdd„deƒZ Gdd „d eƒZ gd ¢Z d S) zCLIPSeg model configurationé)ÚPretrainedConfig)ÚloggingcsFeZdZdZdZdZ         d‡fdd„ Z‡ZS)ÚCLIPSegTextConfiga This is the configuration class to store the configuration of a [`CLIPSegModel`]. It is used to instantiate an CLIPSeg 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 CLIPSeg [CIDAS/clipseg-rd64](https://huggingface.co/CIDAS/clipseg-rd64) 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 CLIPSeg text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`CLIPSegModel`]. 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 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 CLIPSegTextConfig, CLIPSegTextModel >>> # Initializing a CLIPSegTextConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegTextConfig() >>> # Initializing a CLIPSegTextModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zclipseg_text_modelÚ text_configéÁééé ééMÚ quick_geluçñh㈵øä>çç{®Gáz”?çð?ééþÀéÿÀc s`tƒjd| | |dœ|¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ dS)N)Ú pad_token_idÚ bos_token_idÚ eos_token_id©) ÚsuperÚ__init__Ú vocab_sizeÚ hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚmax_position_embeddingsÚlayer_norm_epsÚ hidden_actÚinitializer_rangeÚinitializer_factorÚattention_dropout)Úselfrrrrrrr!r r$r"r#rrrÚkwargs©Ú __class__rú`/var/www/auris/lib/python3.10/site-packages/transformers/models/clipseg/configuration_clipseg.pyrVs zCLIPSegTextConfig.__init__)rrrr r r r r rrrrrr©Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeZbase_config_keyrÚ __classcell__rrr'r)rs&:ñrcsBeZdZdZdZdZ       d‡fdd„ Z‡ZS)ÚCLIPSegVisionConfigaG This is the configuration class to store the configuration of a [`CLIPSegModel`]. It is used to instantiate an CLIPSeg 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 CLIPSeg [CIDAS/clipseg-rd64](https://huggingface.co/CIDAS/clipseg-rd64) 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): 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 CLIPSegVisionConfig, CLIPSegVisionModel >>> # Initializing a CLIPSegVisionConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegVisionConfig() >>> # Initializing a CLIPSegVisionModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zclipseg_vision_modelÚ vision_configéé r réàé r r rrrc  s^tƒjdi| ¤Ž||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ ||_ dS)Nr)rrrrrrÚ num_channelsÚ patch_sizeÚ image_sizer"r#r$r r!)r%rrrrr7r9r8r!r r$r"r#r&r'rr)r¯s zCLIPSegVisionConfig.__init__) r3r4r r rr5r6r r rrrr*rrr'r)r1ws"4ór1c sbeZdZdZdZeedœZddddgd¢dd d d d d df ‡fdd„ Ze dedefdd„ƒZ ‡Z S)Ú CLIPSegConfiga [`CLIPSegConfig`] is the configuration class to store the configuration of a [`CLIPSegModel`]. It is used to instantiate a CLIPSeg 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 CLIPSeg [CIDAS/clipseg-rd64](https://huggingface.co/CIDAS/clipseg-rd64) 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 [`CLIPSegTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`CLIPSegVisionConfig`]. 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 CLIPSeg implementation. extract_layers (`List[int]`, *optional*, defaults to `[3, 6, 9]`): Layers to extract when forwarding the query image through the frozen visual backbone of CLIP. reduce_dim (`int`, *optional*, defaults to 64): Dimensionality to reduce the CLIP vision embedding. decoder_num_attention_heads (`int`, *optional*, defaults to 4): Number of attention heads in the decoder of CLIPSeg. decoder_attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. decoder_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. decoder_intermediate_size (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layers in the Transformer decoder. conditional_layer (`int`, *optional*, defaults to 0): The layer to use of the Transformer encoder whose activations will be combined with the condition embeddings using FiLM (Feature-wise Linear Modulation). If 0, the last layer is used. use_complex_transposed_convolution (`bool`, *optional*, defaults to `False`): Whether to use a more complex transposed convolution in the decoder, enabling more fine-grained segmentation. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import CLIPSegConfig, CLIPSegModel >>> # Initializing a CLIPSegConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegConfig() >>> # Initializing a CLIPSegModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a CLIPSegConfig from a CLIPSegTextConfig and a CLIPSegVisionConfig >>> # Initializing a CLIPSegText and CLIPSegVision configuration >>> config_text = CLIPSegTextConfig() >>> config_vision = CLIPSegVisionConfig() >>> config = CLIPSegConfig.from_text_vision_configs(config_text, config_vision) ```Zclipseg©rr2Nrgƒ/L¦ F@)réé é@érr réFc  sþ|  dd¡}|  dd¡}tƒjdi| ¤Ž|dur]|duri}tdi|¤Ž ¡}| ¡D]+\}}||vrW|||krW|dvrW||vrLd|›d|›d}nd|›d}t |¡q,| |¡|dur¶|durgi}t di|¤Ž ¡}d |vrd d „|d  ¡Dƒ|d <| ¡D]+\}}||vr°|||kr°|dvr°||vr¥d|›d |›d}nd |›d}t |¡q…| |¡|durÁi}t d¡|durÌi}t d¡tdi|¤Ž|_ t di|¤Ž|_ ||_ ||_ ||_||_||_||_| |_| |_| |_d|_| |_dS)NÚtext_config_dictÚvision_config_dict)Ztransformers_versionú`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.zm`text_config_dict` is provided which will be used to initialize `CLIPSegTextConfig`. The value `text_config["z"]` will be overridden.Zid2labelcSsi|] \}}t|ƒ|“qSr)Ústr)Ú.0ÚkeyÚvaluerrr)Ú Psÿz*CLIPSegConfig.__init__..zv` is found in both `vision_config_dict` and `vision_config` but with different values. The value `vision_config_dict["zs`vision_config_dict` is provided which will be used to initialize `CLIPSegVisionConfig`. The value `vision_config["zR`text_config` is `None`. Initializing the `CLIPSegTextConfig` with default values.zV`vision_config` is `None`. initializing the `CLIPSegVisionConfig` with default values.rr)ÚpoprrrÚto_dictÚitemsÚloggerÚinfoÚupdater1rr2Úprojection_dimÚlogit_scale_init_valueÚextract_layersÚ reduce_dimÚdecoder_num_attention_headsÚdecoder_attention_dropoutÚdecoder_hidden_actÚdecoder_intermediate_sizeÚconditional_layerr#Ú"use_complex_transposed_convolution)r%rr2rOrPrQrRrSrTrUrVrWrXr&rArBZ_text_config_dictrFrGÚmessageZ_vision_config_dictr'rr)rs|  ÿÿÿÿ €   ÿÿÿÿÿ €    zCLIPSegConfig.__init__rr2cKs|d| ¡| ¡dœ|¤ŽS)zó Instantiate a [`CLIPSegConfig`] (or a derived class) from clipseg text model configuration and clipseg vision model configuration. Returns: [`CLIPSegConfig`]: An instance of a configuration object r;Nr)rJ)Úclsrr2r&rrr)Úfrom_text_vision_configss z&CLIPSegConfig.from_text_vision_configs) r+r,r-r.r/rr1Z sub_configsrÚ classmethodr[r0rrr'r)r:Ïs&? ómr:)r:rr1N) r.Zconfiguration_utilsrÚutilsrZ get_loggerr+rLrr1r:Ú__all__rrrr)Ús   _X >