`i|9dZddlmZddlmZejeZGddeZGddeZ Gdd eZ Gd d eZ gd Z d S)zSAM model configuration)PretrainedConfig)loggingc6eZdZdZdZ d fd ZxZS) SamPromptEncoderConfiga This is the configuration class to store the configuration of a [`SamPromptEncoder`]. The [`SamPromptEncoder`] module is used to encode the input 2D points and bounding boxes. Instantiating a configuration defaults will yield a similar configuration to that of the SAM-vit-h [facebook/sam-vit-huge](https://huggingface.co/facebook/sam-vit-huge) 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 256): Dimensionality of the hidden states. image_size (`int`, *optional*, defaults to 1024): The expected output resolution of the image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. mask_input_channels (`int`, *optional*, defaults to 16): The number of channels to be fed to the `MaskDecoder` module. num_point_embeddings (`int`, *optional*, defaults to 4): The number of point embeddings to be used. hidden_act (`str`, *optional*, defaults to `"gelu"`): The non-linear activation function in the encoder and pooler. prompt_encoder_configgeluư>c tjdi|||_||_||_||z|_||_||_||_||_ dSN) super__init__ hidden_size image_size patch_sizeimage_embedding_sizemask_input_channelsnum_point_embeddings hidden_actlayer_norm_eps) selfrrrrrrrkwargs __class__s }/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/sam/configuration_sam.pyrzSamPromptEncoderConfig.__init__3sj ""6"""&$$$.*$<!#6 $8!$,)rr r r r r r __name__ __module__ __qualname____doc__base_config_keyr __classcell__rs@rrrse0.O----------rrc<eZdZdZdZ d fd ZxZS) SamMaskDecoderConfiga This is the configuration class to store the configuration of a [`SamMaskDecoder`]. It is used to instantiate a SAM mask decoder to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the SAM-vit-h [facebook/sam-vit-huge](https://huggingface.co/facebook/sam-vit-huge) 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 256): Dimensionality of the hidden states. hidden_act (`str`, *optional*, defaults to `"relu"`): The non-linear activation function used inside the `SamMaskDecoder` module. mlp_dim (`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 2): 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. attention_downsample_rate (`int`, *optional*, defaults to 2): The downsampling rate of the attention layer. num_multimask_outputs (`int`, *optional*, defaults to 3): The number of outputs from the `SamMaskDecoder` module. In the Segment Anything paper, this is set to 3. iou_head_depth (`int`, *optional*, defaults to 3): The number of layers in the IoU head module. iou_head_hidden_dim (`int`, *optional*, defaults to 256): The dimensionality of the hidden states in the IoU head module. layer_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. mask_decoder_configrrelurr c  tjdi| ||_||_||_||_||_||_||_||_ | |_ | |_ dSr) rrrrmlp_dimnum_hidden_layersnum_attention_headsattention_downsample_ratenum_multimask_outputsiou_head_depthiou_head_hidden_dimr) rrrr0r1r2r3r4r5r6rrrs rrzSamMaskDecoderConfig.__init__msv ""6"""&$ !2#6 )B&%:",#6 ,r) rr+r,r-r.r-rrrr r r's@rr)r)IsoB,O"#----------rr)cVeZdZdZdZdZddddddd d d d d dddddgdddffd ZxZS)SamVisionConfiga This is the configuration class to store the configuration of a [`SamVisionModel`]. It is used to instantiate a SAM vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the SAM ViT-h [facebook/sam-vit-huge](https://huggingface.co/facebook/sam-vit-huge) 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. output_channels (`int`, *optional*, defaults to 256): Dimensionality of the output channels in the Patch 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 image. image_size (`int`, *optional*, defaults to 1024): Expected resolution. Target size of the resized input image. patch_size (`int`, *optional*, defaults to 16): Size of the patches to be extracted from the input image. hidden_act (`str`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) layer_norm_eps (`float`, *optional*, defaults to 1e-06): 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 1e-10): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to query, key, value projections. mlp_ratio (`float`, *optional*, defaults to 4.0): Ratio of mlp hidden dim to embedding dim. use_abs_pos (`bool`, *optional*, defaults to `True`): Whether to use absolute position embedding. use_rel_pos (`bool`, *optional*, defaults to `True`): Whether to use relative position embedding. window_size (`int`, *optional*, defaults to 14): Window size for relative position. global_attn_indexes (`list[int]`, *optional*, defaults to `[2, 5, 8, 11]`): The indexes of the global attention layers. num_pos_feats (`int`, *optional*, defaults to 128): The dimensionality of the position embedding. mlp_dim (`int`, *optional*): The dimensionality of the MLP layer in the Transformer encoder. If `None`, defaults to `mlp_ratio * hidden_size`. Example: ```python >>> from transformers import ( ... SamVisionConfig, ... SamVisionModel, ... ) >>> # Initializing a SamVisionConfig with `"facebook/sam-vit-huge"` style configuration >>> configuration = SamVisionConfig() >>> # Initializing a SamVisionModel (with random weights) from the `"facebook/sam-vit-huge"` style configuration >>> model = SamVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` vision_configsam_vision_modelir rr r r r gg|=Tg@)r-r. Nc ltjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_|t)|| zn||_dSr)rrroutput_channelsr1r2 num_channelsrrrrattention_dropoutinitializer_rangeqkv_bias mlp_ratio use_abs_pos use_rel_pos window_sizeglobal_attn_indexes num_pos_featsintr0)rrrAr1r2rBrrrrrCrDrErFrGrHrIrJrKr0rrs rrzSamVisionConfig.__init__s. ""6"""&.!2#6 ($$$,!2!2  "&&&#6 *7>s;2333G r)r!r"r#r$r% model_typerr&r's@rr8r8sB B H&O#J)MM)+T+T+T+T+T+T+T+T+T+Trr8c<eZdZdZdZeeedZ dfd Z xZ S) SamConfiga [`SamConfig`] is the configuration class to store the configuration of a [`SamModel`]. It is used to instantiate a SAM model according to the specified arguments, defining the vision model, prompt-encoder model and mask decoder configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the SAM-ViT-H [facebook/sam-vit-huge](https://huggingface.co/facebook/sam-vit-huge) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vision_config (Union[`dict`, `SamVisionConfig`], *optional*): Dictionary of configuration options used to initialize [`SamVisionConfig`]. prompt_encoder_config (Union[`dict`, `SamPromptEncoderConfig`], *optional*): Dictionary of configuration options used to initialize [`SamPromptEncoderConfig`]. mask_decoder_config (Union[`dict`, `SamMaskDecoderConfig`], *optional*): Dictionary of configuration options used to initialize [`SamMaskDecoderConfig`]. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import ( ... SamVisionConfig, ... SamPromptEncoderConfig, ... SamMaskDecoderConfig, ... SamModel, ... ) >>> # Initializing a SamConfig with `"facebook/sam-vit-huge"` style configuration >>> configuration = SamConfig() >>> # Initializing a SamModel (with random weights) from the `"facebook/sam-vit-huge"` style configuration >>> model = SamModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a SamConfig from a SamVisionConfig, SamPromptEncoderConfig, and SamMaskDecoderConfig >>> # Initializing SAM vision, SAM Q-Former and language model configurations >>> vision_config = SamVisionConfig() >>> prompt_encoder_config = SamPromptEncoderConfig() >>> mask_decoder_config = SamMaskDecoderConfig() >>> config = SamConfig(vision_config, prompt_encoder_config, mask_decoder_config) ```sam)rr*r9N{Gz?c tjdi|||ni}||ni}||ni}t|tr|}t|t r|}t|t r|}tdi||_t di||_t di||_ ||_ dSr) rr isinstancer8to_dictrr)r9rr*rD)rr9rr*rDrrs rrzSamConfig.__init__7s ""6""")6)B  9N9Z 5 5`b5H5T11Z\ m_ 5 5 4)1133M +-C D D D$9$A$A$C$C ! )+? @ @ @"5"="="?"? ,==}==%;%T%T>S%T%T"#7#N#N:M#N#N !2r)NNNrQ) r!r"r#r$rMrr)r8 sub_configsrr&r's@rrOrOsr/ / bJ!73(K"  3333333333rrO)rOr)rr8N) r$configuration_utilsrutilsr get_loggerr!loggerrr)r8rO__all__rrrr[s333333  H % %.-.-.-.-.--.-.-.-b<-<-<-<-<-+<-<-<-~sTsTsTsTsT&sTsTsTlP3P3P3P3P3 P3P3P3f ] \ \r