+
    œ°³jT  ã                   ól   € R t ^ RIHt ^RIHt ^RIHt ]! RR7      ] ! R R]4      4       4       tR.tR# )	z EfficientNet model configuration)Ústrict)ÚPreTrainedConfig)Úauto_docstringzgoogle/efficientnet-b7)Ú
checkpointc                   óš   a a€ ] tR t^t oRtRt^tRtRtRt	^t
RtRtRtRtRtRtRtRtRtRtR	tR
tRtRtRtRtV 3R ltV3R ltRtVtV ;t# )ÚEfficientNetConfigaq  
width_coefficient (`float`, *optional*, defaults to 2.0):
    Scaling coefficient for network width at each stage.
depth_coefficient (`float`, *optional*, defaults to 3.1):
    Scaling coefficient for network depth at each stage.
depth_divisor (`int`, *optional*, defaults to 8):
    A unit of network width.
kernel_sizes (`list[int]`, *optional*, defaults to `[3, 3, 5, 3, 5, 5, 3]`):
    List of kernel sizes to be used in each block.
out_channels (`list[int]`, *optional*, defaults to `[16, 24, 40, 80, 112, 192, 320]`):
    List of output channel sizes to be used in each block for convolutional layers.
depthwise_padding (`list[int]`, *optional*, defaults to `[]`):
    List of block indices with square padding.
num_block_repeats (`list[int]`, *optional*, defaults to `[1, 2, 2, 3, 3, 4, 1]`):
    List of the number of times each block is to repeated.
expand_ratios (`list[int]`, *optional*, defaults to `[1, 6, 6, 6, 6, 6, 6]`):
    List of scaling coefficient of each block.
squeeze_expansion_ratio (`float`, *optional*, defaults to 0.25):
    Squeeze expansion ratio.
pooling_type (`str` or `function`, *optional*, defaults to `"mean"`):
    Type of final pooling to be applied before the dense classification head. Available options are [`"mean"`,
    `"max"`]
batch_norm_momentum (`float`, *optional*, defaults to 0.99):
    The momentum used by the batch normalization layers.
drop_connect_rate (`float`, *optional*, defaults to 0.2):
    The drop rate for skip connections.

Example:
```python
>>> from transformers import EfficientNetConfig, EfficientNetModel

>>> # Initializing a EfficientNet efficientnet-b7 style configuration
>>> configuration = EfficientNetConfig()

>>> # Initializing a model (with random weights) from the efficientnet-b7 style configuration
>>> model = EfficientNetModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```ÚefficientnetiX  g       @gÍÌÌÌÌÌ@g      Ð?Úswishi 
  Úmeang{®Gáz”?gü©ñÒMbP?g®Gáz®ï?g      à?gš™™™™™É?c                ój   <€ \         SV `  ! R/ VB  \        V P                  4      ^,          V n        R# )é   N© )ÚsuperÚ__post_init__ÚsumÚnum_block_repeatsÚnum_hidden_layers)ÚselfÚkwargsÚ	__class__s   &,€Ú|/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/efficientnet/configuration_efficientnet.pyr   Ú EfficientNetConfig.__post_init__Z   s+   ø€ Ü‰ÒÑ' Ò'Ü!$ T×%;Ñ%;Ó!<¸qÕ!@ˆÖó    c                óè  <€ V ^8„  d   Qh/ S[ ;R&   S[ S[S[ ,          ,          S[S[ S[ 3,          ,          ;R&   S[;R&   S[;R&   S[ ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R	&   S[S[ ,          S[S[ R3,          ,          ;R
&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[;R&   S[;R&   S[ ;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[S[ ,          ;R&   S[S[ ,          ;R&   # )é   Únum_channelsÚ
image_sizeÚwidth_coefficientÚdepth_coefficientÚdepth_divisor.Úkernel_sizesÚin_channelsÚout_channelsÚdepthwise_paddingÚstridesr   Úexpand_ratiosÚsqueeze_expansion_ratioÚ
hidden_actÚ
hidden_dimÚpooling_typeÚinitializer_rangeÚbatch_norm_epsÚbatch_norm_momentumÚdropout_rateÚdrop_connect_rate)ÚintÚlistÚtupleÚfloatÚstr)ÚformatÚ__classdict__s   "€r   Ú__annotate__ÚEfficientNetConfig.__annotate__   sÔ  ø‡ ‚ ñ\ Ññ] ñ^ ‘d™3•i•¡%©©S¨¥/Õ1Ñ7ñ_ ñ` Ñ"ña ñb Ñ"ñc ñd Ññe ñf ‘s•)™e¡C¨ H�oÕ-ÑEñg ñh ‘c•™U¡3¨ 8�_Õ,ÑMñi ñj ‘s•)™e¡C¨ H�oÕ-ÑOñk ñl ™C•y¡5©¨c¨¥?Õ2Ñ7ñm ñn ‘#�Y™™s C˜x�Õ(Ñ@ño ñp ™C•y¡5©¨c¨¥?Õ2ÑJñq ñr ™•9™u¡S¨# X�Õ.ÑFñs ñt #Ñ)ñu ñv Ññw ñx Ññy ñz Ññ{ ñ| Ñ#ñ} ñ~ Ñ!ñ ñ@ Ñ%ñA ñB ™#•+Ñ#ñC ñD ™s•{Ñ(òE r   )r   )é   r8   é   r8   r9   r9   r8   )é    é   é   é(   éP   ép   éÀ   )r;   r<   r=   r>   r?   r@   i@  r   )é   r   r   r   rA   r   rA   )rA   r   r   r8   r8   r   rA   )rA   é   rB   rB   rB   rB   rB   ) Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typer   r   r   r   r   r    r!   r"   r#   r$   r   r%   r&   r'   r(   r)   r*   r+   r,   r-   r.   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r   r5   s   @@r   r   r      s‘   ù‡ € ñ'ðR  €Jà€LØ47€JØ"ÐØ"ÐØ€MØ0E€LØ/M€KØ0O€LØ57ÐØ+@€GØ5JÐØ1F€MØ%)ÐØ€JØ€JØ€LØ#ÐØ!€NØ!%ÐØ #€LØ%(ÐõA÷I … r   r   N)	rG   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r   r   r   Ú<module>rQ      sN   ðñ 'å .å 3Ý #ñ Ð3Ô4ØôDAÐ)ó DAó ó 5ðDAðN  Ð
 ‚r   