`iIdZddlmZddlmZejeZGddeZGddeZ Gdd eZ gd Z d S) zCLIPSeg model configuration)PretrainedConfig)loggingcHeZdZdZdZdZ dfd ZxZS)CLIPSegTextConfiga 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 ```clipseg_text_model text_config M quick_geluh㈵>{Gz??c 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_embeddingslayer_norm_eps hidden_actinitializer_rangeinitializer_factorattention_dropout)selfrrr r!r"r#r%r$r(r&r'rrrkwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/clipseg/configuration_clipseg.pyrzCLIPSegTextConfig.__init__Vs$ sl\hsslrsss$&!2!2#6 '>$,$!2"4!2)r r r r r rrrrrrrrr__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__r+s@r,rrs8 8 t&J#O "3333333333r-rcDeZdZdZdZdZ dfd ZxZS)CLIPSegVisionConfigaG 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 ```clipseg_vision_model vision_config r r rrrrrc  tjdi| ||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ ||_ dS)Nr)rrrr r!r" num_channels patch_size image_sizer&r'r(r$r%)r)rr r!r"r@rBrAr%r$r(r&r'r*r+s r,rzCLIPSegVisionConfig.__init__s ""6"""&!2!2#6 ($$!2"4!2,$r-) r;r<r r rr=r>rrrrrr.r6s@r,r8r8wsz2 2 h(J%O%%%%%%%%%%r-r8c NeZdZdZdZeedZddddgddd d d d d df fd ZxZ S) 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) ```clipseg)rr:Nr g/L F@)r @rrr Fc  | dd}| dd}tjdi| ||i}tdi|}|D]I\}}||vr@|||kr4|dkr.||vr d|d|d}nd|d}t |J||||i}tdi|}d |vr'd |d D|d <|D]I\}}||vr@|||kr4|dkr.||vr d|d |d}nd |d}t |J|||i}t d |i}t dtdi||_ tdi||_ ||_ ||_ ||_||_||_||_| |_| |_| |_d|_| |_dS)Ntext_config_dictvision_config_dicttransformers_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.zm`text_config_dict` is provided which will be used to initialize `CLIPSegTextConfig`. The value `text_config["z"]` will be overridden.id2labelc4i|]\}}t||Sr)str).0keyvalues r, z*CLIPSegConfig.__init__..Ps1333(2UCHHe333r-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)poprrrto_dictitemsloggerinfoupdater8rr:projection_dimlogit_scale_init_valueextract_layers reduce_dimdecoder_num_attention_headsdecoder_attention_dropoutdecoder_hidden_actdecoder_intermediate_sizeconditional_layerr'"use_complex_transposed_convolution)r)rr:r]r^r_r`rarbrcrdrerfr*rLrM_text_config_dictrTrUmessage_vision_config_dictr+s r,rzCLIPSegConfig.__init__sX&"::&8$??#ZZ(ros"!333333  H % %\3\3\3\3\3(\3\3\3~U%U%U%U%U%*U%U%U%pnUnUnUnUnU$nUnUnUb H G Gr-