T^(hdZddlmZddlmZddlmZddlmZddl m Z ddl m Z e jeZGd d eZGd d e Zd d gZy )zMobileViTV2 model configuration OrderedDict)Mapping)version)PretrainedConfig) OnnxConfig)loggingc\eZdZdZdZdddddddd d d d gd d dgdgdddddffd ZxZS)MobileViTV2Configa This is the configuration class to store the configuration of a [`MobileViTV2Model`]. It is used to instantiate a MobileViTV2 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 MobileViTV2 [apple/mobilevitv2-1.0](https://huggingface.co/apple/mobilevitv2-1.0) 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 256): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 2): The size (resolution) of each patch. expand_ratio (`float`, *optional*, defaults to 2.0): Expansion factor for the MobileNetv2 layers. hidden_act (`str` or `function`, *optional*, defaults to `"swish"`): The non-linear activation function (function or string) in the Transformer encoder and convolution layers. conv_kernel_size (`int`, *optional*, defaults to 3): The size of the convolutional kernel in the MobileViTV2 layer. output_stride (`int`, *optional*, defaults to 32): The ratio of the spatial resolution of the output to the resolution of the input image. classifier_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for attached classifiers. 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. aspp_out_channels (`int`, *optional*, defaults to 512): Number of output channels used in the ASPP layer for semantic segmentation. atrous_rates (`List[int]`, *optional*, defaults to `[6, 12, 18]`): Dilation (atrous) factors used in the ASPP layer for semantic segmentation. aspp_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the ASPP layer for semantic segmentation. semantic_loss_ignore_index (`int`, *optional*, defaults to 255): The index that is ignored by the loss function of the semantic segmentation model. n_attn_blocks (`List[int]`, *optional*, defaults to `[2, 4, 3]`): The number of attention blocks in each MobileViTV2Layer base_attn_unit_dims (`List[int]`, *optional*, defaults to `[128, 192, 256]`): The base multiplier for dimensions of attention blocks in each MobileViTV2Layer width_multiplier (`float`, *optional*, defaults to 1.0): The width multiplier for MobileViTV2. ffn_multiplier (`int`, *optional*, defaults to 2): The FFN multiplier for MobileViTV2. attn_dropout (`float`, *optional*, defaults to 0.0): The dropout in the attention layer. ffn_dropout (`float`, *optional*, defaults to 0.0): The dropout between FFN layers. Example: ```python >>> from transformers import MobileViTV2Config, MobileViTV2Model >>> # Initializing a mobilevitv2-small style configuration >>> configuration = MobileViTV2Config() >>> # Initializing a model from the mobilevitv2-small style configuration >>> model = MobileViTV2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` mobilevitv2rg@swish g?g{Gz?gh㈵>i) )rr)rg?gc <t|di|||_||_||_||_||_||_||_| |_ | |_ ||_ ||_ ||_ ||_||_||_||_| |_| |_| |_||_y)N)super__init__ num_channels image_size patch_size expand_ratio hidden_actconv_kernel_size output_strideinitializer_rangelayer_norm_eps n_attn_blocksbase_attn_unit_dimswidth_multiplierffn_multiplier ffn_dropout attn_dropoutclassifier_dropout_probaspp_out_channels atrous_ratesaspp_dropout_probsemantic_loss_ignore_index)selfrrrr r!r"r#r,r$r%r-r.r/r0r&r'r(r)r+r*kwargs __class__s w/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/mobilevitv2/configuration_mobilevitv2.pyrzMobileViTV2Config.__init__cs0 "6"($$($ 0*!2,*#6 0,&('>$"3(!2*D')__name__ __module__ __qualname____doc__ model_typer __classcell__)r3s@r4r r s[@ DJ # #&++/E/Er5r ceZdZejdZedeeee efffdZ edeeee efffdZ ede fdZ y)MobileViTV2OnnxConfigz1.11returnc(tddddddfgS)N pixel_valuesbatchrheightwidth)rrrrr1s r4inputszMobileViTV2OnnxConfig.inputss ^^PX]d-efghhr5cj|jdk(rtdddifgStdddifdddifgS)Nzimage-classificationlogitsrrAlast_hidden_state pooler_output)taskrrEs r4outputszMobileViTV2OnnxConfig.outputssL 99. .Aw< 89: :!4q'l CoXY[bWcEdef fr5cy)Ng-C6?rrEs r4atol_for_validationz)MobileViTV2OnnxConfig.atol_for_validationsr5N)r6r7r8rparsetorch_onnx_minimum_versionpropertyrstrintrFrLfloatrNrr5r4r=r=s!.v!6 iWS#X%6 67iiggc3h&7!78gg Ur5r=N)r9 collectionsrtypingr packagingrconfiguration_utilsronnxr utilsr get_loggerr6loggerr r=__all__rr5r4r^s[&#3   H %tE(tEnJ&  7 8r5