fTh{rSrSSKJr SSKJr SSKJrJr \R"\ 5r "SS\\5r S/r g)z&Swinv2 Transformer model configuration)PretrainedConfig)logging)BackboneConfigMixin*get_aligned_output_features_output_indicescr^\rSrSrSrSrSSS.rSSS S /S Q/S QS /SQSSSSSSSSSSSS4U4SjjrSrU=r $) Swinv2Configa This is the configuration class to store the configuration of a [`Swinv2Model`]. It is used to instantiate a Swin Transformer v2 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 Transformer v2 [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) 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. pretrained_window_sizes (`list(int)`, *optional*, defaults to `[0, 0, 0, 0]`): Size of windows during pretraining. 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. 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. Example: ```python >>> from transformers import Swinv2Config, Swinv2Model >>> # Initializing a Swinv2 microsoft/swinv2-tiny-patch4-window8-256 style configuration >>> configuration = Swinv2Config() >>> # Initializing a model (with random weights) from the microsoft/swinv2-tiny-patch4-window8-256 style configuration >>> model = Swinv2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```swinv2 num_heads num_layers)num_attention_headsnum_hidden_layersr`)rr)rr )rrrg@Tgg?geluFg{Gz?gh㈵> Nc >[TU]"S0UD6 XlX lX0lX@lXPl[U5UlX`l Xpl Xl Xl Xl XlXlXlXlXlUUlUUlUUlS/[-S[U5S-5Vs/sHnSU3PM sn-Ul[1UUUR.S9uUlUl[7US[U5S- --5Ulgs snf)Nstemstage) out_features out_indices stage_namesr)super__init__ image_size patch_size num_channels embed_dimdepthslenr r window_sizepretrained_window_sizes mlp_ratioqkv_biashidden_dropout_probattention_probs_dropout_probdrop_path_rate hidden_actuse_absolute_embeddingslayer_norm_epsinitializer_rangeencoder_strideranger r _out_features _out_indicesint hidden_size)selfr$r%r&r'r(r r*r+r,r-r.r/r0r1r2r4r3r5rrkwargsidx __class__s g/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/swinv2/configuration_swinv2.pyr#Swinv2Config.__init__is 0 "6"$$(" f+"&'>$" #6 ,H),$'>$,!2,"8aVWX@Y&Z@Yse}@Y&ZZ0Z%;DL\L\1 -D- y1Vq+AAB '[s-D )r7r8r/r(r0r'r5r1r.r:r$r4r3r,r&r r r%r+r-r r2r*) __name__ __module__ __qualname____firstlineno____doc__ model_type attribute_mapr#__static_attributes__ __classcell__)r>s@r?rrsjF PJ +)M  ,%( %+3C3CrN) rEconfiguration_utilsrutilsrutils.backbone_utilsrr get_loggerrAloggerr__all__r!rJr?rQsD-3c   H %CC&(8CCL  rJ