
    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ResNet model configuration    OrderedDict)Mapping)version   )PretrainedConfig)
OnnxConfig)logging)BackboneConfigMixin*get_aligned_output_features_output_indicesc            
       L     e Zd ZdZdZddgZddg dg ddd	d
d
ddf
 fd	Z xZS )ResNetConfiga  
    This is the configuration class to store the configuration of a [`ResNetModel`]. It is used to instantiate an
    ResNet 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 ResNet
    [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) architecture.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.

    Args:
        num_channels (`int`, *optional*, defaults to 3):
            The number of input channels.
        embedding_size (`int`, *optional*, defaults to 64):
            Dimensionality (hidden size) for the embedding layer.
        hidden_sizes (`List[int]`, *optional*, defaults to `[256, 512, 1024, 2048]`):
            Dimensionality (hidden size) at each stage.
        depths (`List[int]`, *optional*, defaults to `[3, 4, 6, 3]`):
            Depth (number of layers) for each stage.
        layer_type (`str`, *optional*, defaults to `"bottleneck"`):
            The layer to use, it can be either `"basic"` (used for smaller models, like resnet-18 or resnet-34) or
            `"bottleneck"` (used for larger models like resnet-50 and above).
        hidden_act (`str`, *optional*, defaults to `"relu"`):
            The non-linear activation function in each block. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"`
            are supported.
        downsample_in_first_stage (`bool`, *optional*, defaults to `False`):
            If `True`, the first stage will downsample the inputs using a `stride` of 2.
        downsample_in_bottleneck (`bool`, *optional*, defaults to `False`):
            If `True`, the first conv 1x1 in ResNetBottleNeckLayer will downsample the inputs using a `stride` of 2.
        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 ResNetConfig, ResNetModel

    >>> # Initializing a ResNet resnet-50 style configuration
    >>> configuration = ResNetConfig()

    >>> # Initializing a model (with random weights) from the resnet-50 style configuration
    >>> model = ResNetModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```
    resnetbasic
bottleneckr   @   )   i   i   i   )r         r   reluFNc                    t        |   di | || j                  vr*t        d| ddj	                  | j                               || _        || _        || _        || _        || _	        || _
        || _        || _        dgt        dt        |      dz         D cg c]  }d| 	 c}z   | _        t!        |	|
| j                        \  | _        | _        y c c}w )	Nzlayer_type=z is not one of ,stem   stage)out_featuresout_indicesstage_names )super__init__layer_types
ValueErrorjoinnum_channelsembedding_sizehidden_sizesdepths
layer_type
hidden_actdownsample_in_first_stagedownsample_in_bottleneckrangelenr   r   _out_features_out_indices)selfr%   r&   r'   r(   r)   r*   r+   r,   r   r   kwargsidx	__class__s                b/var/www/html/venv/lib/python3.12/site-packages/transformers/models/resnet/configuration_resnet.pyr!   zResNetConfig.__init__Y   s     	"6"T---{:,ochhtO_O_F`Eabcc(,($$)B&(@%"8aVWX@Y&Zse}&ZZ0Z%;DL\L\1
-D- '[s   C)__name__
__module____qualname____doc__
model_typer"   r!   __classcell__)r4   s   @r5   r   r      sD    4l JL)K +"'!&
 
    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)ResNetOnnxConfigz1.11returnc                 (    t        ddddddfg      S )Npixel_valuesbatchr%   heightwidth)r   r      r   r   r1   s    r5   inputszResNetOnnxConfig.inputs{   s&    WHQX!YZ
 	
r<   c                      y)NgMbP?r   rF   s    r5   atol_for_validationz$ResNetOnnxConfig.atol_for_validation   s    r<   N)r6   r7   r8   r   parsetorch_onnx_minimum_versionpropertyr   strintrG   floatrI   r   r<   r5   r>   r>   x   sZ    !.v!6
WS#X%6 67 
 
 U  r<   r>   N)r9   collectionsr   typingr   	packagingr   configuration_utilsr   onnxr	   utilsr
   utils.backbone_utilsr   r   
get_loggerr6   loggerr   r>   r   r<   r5   <module>rY      sR    ! #   3   c 
		H	%V
&(8 V
rz r<   