qiMndZddlmZddlmZddlmZejeZ GddeeZ dgZ y)z$Swin Transformer model configuration)BackboneConfigMixin)PreTrainedConfig)loggingc`eZdZdZdZdddZdddd gd gd d d dddddddddddffd ZxZS) SwinConfiga This is the configuration class to store the configuration of a [`SwinModel`]. It is used to instantiate a Swin 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 Swin [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 4): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. embed_dim (`int`, *optional*, defaults to 96): Dimensionality of patch embedding. depths (`list(int)`, *optional*, defaults to `[2, 2, 6, 2]`): Depth of each layer in the Transformer encoder. num_heads (`list(int)`, *optional*, defaults to `[3, 6, 12, 24]`): Number of attention heads in each layer of the Transformer encoder. window_size (`int`, *optional*, defaults to 7): Size of windows. mlp_ratio (`float`, *optional*, defaults to 4.0): Ratio of MLP hidden dimensionality to embedding dimensionality. qkv_bias (`bool`, *optional*, defaults to `True`): Whether or not a learnable bias should be added to the queries, keys and values. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings and encoder. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. drop_path_rate (`float`, *optional*, defaults to 0.1): Stochastic depth rate. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. use_absolute_embeddings (`bool`, *optional*, defaults to `False`): Whether or not to add absolute position embeddings to the patch embeddings. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. encoder_stride (`int`, *optional*, defaults to 32): Factor to increase the spatial resolution by in the decoder head for masked image modeling. out_features (`list[str]`, *optional*): If used as backbone, list of features to output. Can be any of `"stem"`, `"stage1"`, `"stage2"`, etc. (depending on how many stages the model has). If unset and `out_indices` is set, will default to the corresponding stages. If unset and `out_indices` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. out_indices (`list[int]`, *optional*): If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). If unset and `out_features` is set, will default to the corresponding stages. If unset and `out_features` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. Example: ```python >>> from transformers import SwinConfig, SwinModel >>> # Initializing a Swin microsoft/swin-tiny-patch4-window7-224 style configuration >>> configuration = SwinConfig() >>> # Initializing a model (with random weights) from the microsoft/swin-tiny-patch4-window7-224 style configuration >>> model = SwinModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```swin num_heads num_layers)num_attention_headsnum_hidden_layersr`)rr)rr g@Tgg?geluFg{Gz?gh㈵> Nc t|di|||_||_||_||_||_t||_||_ ||_ ||_ | |_ | |_ | |_| |_| |_||_||_||_||_t+|dt|dz zz|_dgt/dt|dzDcgc]}d| c}z|_|j3||ycc}w)Nrstemstage) out_indices out_features)super__init__ image_size patch_size num_channels embed_dimdepthslenr r window_size mlp_ratioqkv_biashidden_dropout_probattention_probs_dropout_probdrop_path_rate hidden_actuse_absolute_embeddingslayer_norm_epsinitializer_rangeencoder_strideint hidden_sizerange stage_names"set_output_features_output_indices)selfr r!r"r#r$r r&r'r(r)r*r+r,r-r/r.r0rrkwargsidx __class__s ]/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/swin/configuration_swin.pyrzSwinConfig.__init__hs . "6"$$(" f+"&"  #6 ,H),$'>$,!2,y1Vq+AAB"8aVWX@Y&Zse}&ZZ //KVb/c'[s D)__name__ __module__ __qualname____doc__ model_type attribute_mapr __classcell__)r9s@r:rrsgF PJ +)M %( %)/d/drN) r>backbone_utilsrconfiguration_utilsrutilsr get_loggerr;loggerr__all__rrBr:rIsE+13   H %d$&6dD .rB