Ë
    ©sg^  ã                   ól   — d Z ddlmZ ddlmZ ddlmZmZ  ej                  e	«      Z
 G d„ dee«      Zy)z&Swinv2 Transformer model configurationé   )ÚPretrainedConfig)Úlogging)ÚBackboneConfigMixinÚ*get_aligned_output_features_output_indicesc                   óf   ‡ — e Zd ZdZdZdddœZdddd	g d
¢g d¢dg d¢ddddddddddddfˆ fd„	Zˆ xZS )Ú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
    ```Úswinv2Ú	num_headsÚ
num_layers)Únum_attention_headsÚnum_hidden_layerséà   é   r   é`   )é   r   é   r   )r   r   é   é   é   )é    r   r   r   g      @Tg        gš™™™™™¹?ÚgeluFg{®Gáz”?gñhãˆµøä>é    Nc                 ó<  •— t        ‰|   di |¤Ž || _        || _        || _        || _        || _        t        |«      | _        || _	        || _
        || _        |	| _        |
| _        || _        || _        || _        || _        || _        || _        || _        || _        dgt-        dt        |«      dz   «      D cg c]  }d|› ‘Œ	 c}z   | _        t1        ||| j.                  ¬«      \  | _        | _        t7        |dt        |«      dz
  z  z  «      | _        y c c}w )NÚstemé   Ústage)Úout_featuresÚout_indicesÚstage_namesr   © )ÚsuperÚ__init__Ú
image_sizeÚ
patch_sizeÚnum_channelsÚ	embed_dimÚdepthsÚlenr   r
   Úwindow_sizeÚpretrained_window_sizesÚ	mlp_ratioÚqkv_biasÚhidden_dropout_probÚattention_probs_dropout_probÚdrop_path_rateÚ
hidden_actÚuse_absolute_embeddingsÚlayer_norm_epsÚinitializer_rangeÚencoder_strideÚranger   r   Ú_out_featuresÚ_out_indicesÚintÚhidden_size)Úselfr#   r$   r%   r&   r'   r
   r)   r*   r+   r,   r-   r.   r/   r0   r1   r3   r2   r4   r   r   ÚkwargsÚidxÚ	__class__s                          €úb/var/www/html/venv/lib/python3.12/site-packages/transformers/models/swinv2/configuration_swinv2.pyr"   zSwinv2Config.__init__i   s!  ø€ ô0 	‰ÑÑ"˜6Ò"à$ˆŒØ$ˆŒØ(ˆÔØ"ˆŒØˆŒÜ˜f›+ˆŒØ"ˆŒØ&ˆÔØ'>ˆÔ$Ø"ˆŒØ ˆŒØ#6ˆÔ Ø,HˆÔ)Ø,ˆÔØ$ˆŒØ'>ˆÔ$Ø,ˆÔØ!2ˆÔØ,ˆÔØ"˜8ÄÀaÌÈVËÐWXÉÓ@YÖ&Z¸¨¨s¨e¢}Ò&ZÑZˆÔÜ0ZØ%°;ÈD×L\ÑL\ô1
Ñ-ˆÔ˜DÔ-ô
 ˜y¨1´°V³¸q±Ñ+AÑAÓBˆÕùò '[s   Â;D)Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚattribute_mapr"   Ú__classcell__)r=   s   @r>   r   r      sj   ø„ ñFðP €Jð  +Ø)ñ€Mð ØØØÚÚ ØÚ ,ØØØØ%(ØØØ %ØØØØØ÷+3Cñ 3Có    r   N)rB   Úconfiguration_utilsr   Úutilsr   Úutils.backbone_utilsr   r   Ú
get_loggerr?   Úloggerr   r    rF   r>   ú<module>rL      s;   ðñ -å 3Ý ß cð 
ˆ×	Ñ	˜HÓ	%€ôCCÐ&Ð(8õ CCrF   