U Ö9%eEã@s‚dZddlmZddlmZddlmZddlmZddl m Z ddl m Z e   e¡Zd d iZGd d „d eƒZGd d„de ƒZdS)z MobileViTV2 model configurationé©Ú OrderedDict)ÚMapping)Úversioné)ÚPretrainedConfig)Ú OnnxConfig)Úloggingzapple/mobilevitv2-1.0zEhttps://huggingface.co/apple/mobilevitv2-1.0/resolve/main/config.jsoncs`eZdZdZdZdddddddd d d d d ddgd ddddgdddgddddf‡fdd„ Z‡ZS)ÚMobileViTV2Configa« 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-5): 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 ```Z mobilevitv2réég@Zswishé gš™™™™™¹?g{®Gáz”?gñh㈵øä>iéé ééÿéé€éÀgð?gc sŠtƒjf|Ž||_||_||_||_||_||_||_| |_ | |_ ||_ ||_ ||_ ||_||_||_||_| |_| |_| |_||_dS)N)ÚsuperÚ__init__Ú num_channelsÚ image_sizeÚ patch_sizeÚ expand_ratioÚ hidden_actÚconv_kernel_sizeÚ output_strideÚinitializer_rangeÚlayer_norm_epsÚ n_attn_blocksÚbase_attn_unit_dimsÚwidth_multiplierÚffn_multiplierÚ ffn_dropoutÚ attn_dropoutÚclassifier_dropout_probÚaspp_out_channelsÚ atrous_ratesÚaspp_dropout_probÚsemantic_loss_ignore_index)Úselfrrrrrrrr&rrr'r(r)r*r r!r"r#r%r$Úkwargs©Ú __class__©úx/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/mobilevitv2/configuration_mobilevitv2.pyrfs*zMobileViTV2Config.__init__)Ú__name__Ú __module__Ú __qualname__Ú__doc__Z model_typerÚ __classcell__r/r/r-r0r "s.Aër c@sleZdZe d¡Zeeeee effdœdd„ƒZ eeeee effdœdd„ƒZ ee dœdd„ƒZ d S) ÚMobileViTV2OnnxConfigz1.11)ÚreturncCstddddddœfgƒS)NZ pixel_valuesÚbatchrÚheightÚwidth)rér rr©r+r/r/r0Úinputs›szMobileViTV2OnnxConfig.inputscCs<|jdkrtdddifgƒStdddifdddifgƒSdS)Nzimage-classificationZlogitsrr8Zlast_hidden_stateZ pooler_output)Útaskrr<r/r/r0ÚoutputsŸs zMobileViTV2OnnxConfig.outputscCsdS)Ng-Cëâ6?r/r<r/r/r0Úatol_for_validation¦sz)MobileViTV2OnnxConfig.atol_for_validationN)r1r2r3rÚparseZtorch_onnx_minimum_versionÚpropertyrÚstrÚintr=r?Úfloatr@r/r/r/r0r6˜s   r6N)r4Ú collectionsrÚtypingrÚ packagingrZconfiguration_utilsrZonnxrÚutilsr Z get_loggerr1ÚloggerZ)MOBILEVITV2_PRETRAINED_CONFIG_ARCHIVE_MAPr r6r/r/r/r0Ús       ÿv