o ZŽh£ã@s‚dZddlmZddlmZddlmZddlmZddl m Z ddl m Z e   e¡ZGd d „d eƒZGd d „d e ƒZd d gZd S)zMobileViT model configurationé©Ú OrderedDict)ÚMapping)Úversioné)ÚPretrainedConfig)Ú OnnxConfig)Úloggingcs\eZdZdZdZdddgd¢gd¢dd d d dd d dd ddddgd¢d df‡fdd„ Z‡ZS)ÚMobileViTConfigaë This is the configuration class to store the configuration of a [`MobileViTModel`]. It is used to instantiate a MobileViT 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 MobileViT [apple/mobilevit-small](https://huggingface.co/apple/mobilevit-small) 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. hidden_sizes (`List[int]`, *optional*, defaults to `[144, 192, 240]`): Dimensionality (hidden size) of the Transformer encoders at each stage. neck_hidden_sizes (`List[int]`, *optional*, defaults to `[16, 32, 64, 96, 128, 160, 640]`): The number of channels for the feature maps of the backbone. num_attention_heads (`int`, *optional*, defaults to 4): Number of attention heads for each attention layer in the Transformer encoder. mlp_ratio (`float`, *optional*, defaults to 2.0): The ratio of the number of channels in the output of the MLP to the number of channels in the input. expand_ratio (`float`, *optional*, defaults to 4.0): Expansion factor for the MobileNetv2 layers. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): 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 MobileViT layer. output_stride (`int`, *optional*, defaults to 32): The ratio of the spatial resolution of the output to the resolution of the input image. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the Transformer encoder. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. 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. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. aspp_out_channels (`int`, *optional*, defaults to 256): 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. Example: ```python >>> from transformers import MobileViTConfig, MobileViTModel >>> # Initializing a mobilevit-small style configuration >>> configuration = MobileViTConfig() >>> # Initializing a model from the mobilevit-small style configuration >>> model = MobileViTModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Z mobilevitréé)ééÀéð)éé é@é`é€é i€ég@g@Zsilurgš™™™™™¹?gg{®Gáz”?gñh㈵øä>T)éé ééÿc s”tƒjdi|¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_||_||_||_dS)N©)ÚsuperÚ__init__Ú num_channelsÚ image_sizeÚ patch_sizeÚ hidden_sizesÚneck_hidden_sizesÚnum_attention_headsÚ mlp_ratioÚ expand_ratioÚ hidden_actÚconv_kernel_sizeÚ output_strideÚhidden_dropout_probÚattention_probs_dropout_probÚclassifier_dropout_probÚinitializer_rangeÚlayer_norm_epsÚqkv_biasÚaspp_out_channelsÚ atrous_ratesÚaspp_dropout_probÚsemantic_loss_ignore_index)Úselfrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2Úkwargs©Ú __class__rúd/var/www/auris/lib/python3.10/site-packages/transformers/models/mobilevit/configuration_mobilevit.pyres, zMobileViTConfig.__init__)Ú__name__Ú __module__Ú __qualname__Ú__doc__Z model_typerÚ __classcell__rrr5r7r s2Dêr c@sleZdZe d¡Zedeeee efffdd„ƒZ edeeee efffdd„ƒZ ede fdd„ƒZ d S) ÚMobileViTOnnxConfigz1.11ÚreturncCstddddddœfgƒS)NZ pixel_valuesÚbatchrÚheightÚwidth)rér rr©r3rrr7ÚinputsœszMobileViTOnnxConfig.inputscCs8|jdkrtdddifgƒStdddifdddifgƒS)Nzimage-classificationZlogitsrr?Zlast_hidden_stateZ pooler_output)ÚtaskrrCrrr7Úoutputs s zMobileViTOnnxConfig.outputscCsdS)Ng-Cëâ6?rrCrrr7Úatol_for_validation§sz'MobileViTOnnxConfig.atol_for_validationN)r8r9r:rÚparseZtorch_onnx_minimum_versionÚpropertyrÚstrÚintrDrFÚfloatrGrrrr7r=™s   r=N)r;Ú collectionsrÚtypingrÚ packagingrZconfiguration_utilsrZonnxrÚutilsr Z get_loggerr8Úloggerr r=Ú__all__rrrr7Ús       {