S^(hdZddlmZddlmZmZddlmZddlm Z ddl m Z ddl m Z e jeZGd d e ZGd d e Zd d gZy )z EfficientNet model configuration OrderedDict)ListMapping)version)PretrainedConfig) OnnxConfig)loggingc+eZdZdZdZdddddgdgd gd ggd gd gd dddddddddfdedededededeedeedeedeed eed!eed"eed#ed$ed%ed&ed'ed(ed)ed*ed+ef*fd, Z xZ S)-EfficientNetConfiga# This is the configuration class to store the configuration of a [`EfficientNetModel`]. It is used to instantiate an EfficientNet 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 EfficientNet [google/efficientnet-b7](https://huggingface.co/google/efficientnet-b7) 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. image_size (`int`, *optional*, defaults to 600): The input image size. 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. in_channels (`List[int]`, *optional*, defaults to `[32, 16, 24, 40, 80, 112, 192]`): List of input channel sizes to be used in each block for convolutional layers. 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. strides (`List[int]`, *optional*, defaults to `[1, 2, 2, 2, 1, 2, 1]`): List of stride sizes to be used in each block for convolutional layers. 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. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in each block. If string, `"gelu"`, `"relu"`, `"selu", `"gelu_new"`, `"silu"` and `"mish"` are supported. hiddem_dim (`int`, *optional*, defaults to 1280): The hidden dimension of the layer before the classification head. 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"`] initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. batch_norm_eps (`float`, *optional*, defaults to 1e-3): The epsilon used by the batch normalization layers. batch_norm_momentum (`float`, *optional*, defaults to 0.99): The momentum used by the batch normalization layers. dropout_rate (`float`, *optional*, defaults to 0.5): The dropout rate to be applied before final classifier layer. 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 ``` efficientnetriXg@g@)rrrrrr) (Pp)rrrrrri@)rrrrr)rrrrrr)rrrrrrg?swishi meang{Gz?gMbP?gGz?g?g? num_channels image_sizewidth_coefficientdepth_coefficient depth_divisor kernel_sizes in_channels out_channelsdepthwise_paddingstridesnum_block_repeats expand_ratiossqueeze_expansion_ratio hidden_act hidden_dim pooling_typeinitializer_rangebatch_norm_epsbatch_norm_momentum dropout_ratedrop_connect_ratec pt|di|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_||_||_||_t/| dz|_y)Nr)super__init__rrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2sumnum_hidden_layers)selfrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2kwargs __class__s y/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/efficientnet/configuration_efficientnet.pyr6zEfficientNetConfig.__init__fs2 "6"($!2!2*(&(!2 !2*'>$$$(!2,#6 (!2!$%6!7!!;) __name__ __module__ __qualname____doc__ model_typeintfloatrstrr6 __classcell__)r;s@r<r r sHC J J#&#&"7!?"A')2'<#8)-!"#' %%)!#&-0<0<0<! 0< ! 0<  0<3i0<#Y0<3i0< 90<c0< 90<Cy0<"'0<0< !0<"#0<$!%0<&'0<(#)0<*+0<,!-0<0r4rOs r<atol_for_validationz*EfficientNetOnnxConfig.atol_for_validationsr=N) r>r?r@rparsetorch_onnx_minimum_versionpropertyrrErCrPrDrRr4r=r<rHrHsZ!.v!6  WS#X%6 67  Ur=rHN)rA collectionsrtypingrr packagingrconfiguration_utilsr onnxr utilsr get_loggerr>loggerr rH__all__r4r=r<r_sY'# 3   H %x<)x