
    sg                         d Z ddlmZ ddlmZ ddlmZ ddlm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 G d de
      Zy)z$Swin Transformer model configuration    OrderedDict)Mapping)version   )PretrainedConfig)
OnnxConfig)logging)BackboneConfigMixin*get_aligned_output_features_output_indicesc                   `     e Zd ZdZdZdddZdddd	g d
g ddddddddddddddf fd	Z xZS )
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_headsnum_hidden_layers      r   `   )   r      r   )r   r            g      @Tg        g?geluFg{Gz?gh㈵>    Nc                 .   t        |   di | || _        || _        || _        || _        || _        t        |      | _        || _	        || _
        || _        |	| _        |
| _        || _        || _        || _        || _        || _        || _        || _        t+        |dt        |      dz
  z  z        | _        dgt/        dt        |      dz         D cg c]  }d| 	 c}z   | _        t3        ||| j0                        \  | _        | _        y c c}w )Nr      stemstage)out_featuresout_indicesstage_names )super__init__
image_size
patch_sizenum_channels	embed_dimdepthslenr   r   window_size	mlp_ratioqkv_biashidden_dropout_probattention_probs_dropout_probdrop_path_rate
hidden_actuse_absolute_embeddingslayer_norm_epsinitializer_rangeencoder_strideinthidden_sizeranger$   r   _out_features_out_indices)selfr(   r)   r*   r+   r,   r   r.   r/   r0   r1   r2   r3   r4   r5   r7   r6   r8   r"   r#   kwargsidx	__class__s                         ^/var/www/html/venv/lib/python3.12/site-packages/transformers/models/swin/configuration_swin.pyr'   zSwinConfig.__init__o   s   . 	"6"$$("f+"&" #6 ,H),$'>$,!2, y1Vq+AAB"8aVWX@Y&Zse}&ZZ0Z%;DL\L\1
-D- '[s   D)__name__
__module____qualname____doc__
model_typeattribute_mapr'   __classcell__)rA   s   @rB   r   r      se    FP J  +)M  %( %)1
 1
    r   c                   p    e Zd Z ej                  d      Zedeeee	ef   f   fd       Z
edefd       Zy)SwinOnnxConfigz1.11returnc                 (    t        ddddddfg      S )Npixel_valuesbatchr*   heightwidth)r   r   r   r   r   r>   s    rB   inputszSwinOnnxConfig.inputs   s&    WHQX!YZ
 	
rJ   c                      y)Ng-C6?r%   rS   s    rB   atol_for_validationz"SwinOnnxConfig.atol_for_validation   s    rJ   N)rC   rD   rE   r   parsetorch_onnx_minimum_versionpropertyr   strr9   rT   floatrV   r%   rJ   rB   rL   rL      sZ    !.v!6
WS#X%6 67 
 
 U  rJ   rL   N)rF   collectionsr   typingr   	packagingr   configuration_utilsr   onnxr	   utilsr
   utils.backbone_utilsr   r   
get_loggerrC   loggerr   rL   r%   rJ   rB   <module>re      sR    + #   3   c 
		H	%A
$&6 A
HZ rJ   