fTh|9SrSSKJr SSKJr \R "\5r"SS\5r"SS\5r "SS \5r "S S \5r /S Qr g )zSAM model configuration)PretrainedConfig)loggingcB^\rSrSrSrSrSU4SjjrSrU=r$)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_configc >[T U]"S0UD6 XlX lX0lX#-UlX@lXPlX`lXpl gN) super__init__ hidden_size image_size patch_sizeimage_embedding_sizemask_input_channelsnum_point_embeddings hidden_actlayer_norm_eps) selfrrrrrrrkwargs __class__s a/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/sam/configuration_sam.pyr SamPromptEncoderConfig.__init__3sG "6"&$$$.$<!#6 $8!$,)rrrrrrrr)rgeluư> __name__ __module__ __qualname____firstlineno____doc__base_config_keyr __static_attributes__ __classcell__rs@rrrs00.O--rrcH^\rSrSrSrSrSU4SjjrSrU=r$)SamMaskDecoderConfigIaO 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_configc  >[T U]"S0U D6 XlX lX0lX@lXPlX`lXplXl Xl Xl gr ) r r rrmlp_dimnum_hidden_layersnum_attention_headsattention_downsample_ratenum_multimask_outputsiou_head_depthiou_head_hidden_dimr) rrrr1r2r3r4r5r6r7rrrs rr SamMaskDecoderConfig.__init__msO "6"&$ !2#6 )B&%:",#6 ,r) r4rrr6r7rr1r3r2r5) rreluir:rrrr!r"r+s@rr-r-Is:B,O"#--rr-cb^\rSrSrSrSrSrSSSSSS S S S S SSSSSS/SQSS4U4SjjrSrU=r $)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 rrrr r!gg|=Tg@)r:r; Nc >>[TU]"S0UD6 XlX lX0lX@lXPlX`lXplXl Xl Xl Xl Xl XlXlXlUUlUUlUUlUc[)X-5UlgUUlgr )r r routput_channelsr2r3 num_channelsrrrrattention_dropoutinitializer_rangeqkv_bias mlp_ratio use_abs_pos use_rel_pos window_sizeglobal_attn_indexes num_pos_featsintr1)rrrGr2r3rHrrrrrIrJrKrLrMrNrOrPrQr1rrs rr SamVisionConfig.__init__s. "6"&.!2#6 ($$$,!2!2 "&&&#6 *7>s;23 G r)rIrPrrrrJrr1rLr3rHr2rQrGrrKrMrNrO) r#r$r%r&r'r( model_typer r)r*r+s@rr=r=s]B H&O#J))+T+Trr=cH^\rSrSrSrSr\\\S.r SU4Sjjr Sr U=r $) 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/r?c >[TU]"S0UD6 UbUO0nUbUO0nUbUO0n[U[5(aUR 5n[U[ 5(aUR 5n[U[ 5(aUR 5n[S0UD6Ul[ S0UD6Ul[ S0UD6Ul X@l gr ) r r isinstancer=to_dictrr-r?rr/rJ)rr?rr/rJrrs rr SamConfig.__init__7s "6")6)B  9N9Z 5`b5H5T1Z\ m_ 5 5)113M +-C D D$9$A$A$C ! )+? @ @"5"="="? ,=}=%;%T>S%T"#7#N:M#N !2r)rJr/rr?)NNNg{Gz?) r#r$r%r&r'rTrr-r= sub_configsr r)r*r+s@rrVrVs8/ bJ!73(K"  33rrV)rVr-rr=N) r'configuration_utilsrutilsr get_loggerr#loggerrr-r=rV__all__r rrrcsh3   H %.--.-b<-+<-~sT&sTlP3 P3f ]r