U 9%e*@sdZddlmZddlmZddlmZddlmZddl m Z ddl m Z e eZd d iZGd d d eZGd dde ZdS)z LeViT model configuration OrderedDict)Mapping)version)PretrainedConfig) OnnxConfig)loggingzfacebook/levit-128SzChttps://huggingface.co/facebook/levit-128S/resolve/main/config.jsoncsfeZdZdZdZdddddddd d gd d d gd d d gdddgddddgdddgdffdd ZZS) LevitConfiga This is the configuration class to store the configuration of a [`LevitModel`]. It is used to instantiate a LeViT 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 LeViT [facebook/levit-128S](https://huggingface.co/facebook/levit-128S) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: image_size (`int`, *optional*, defaults to 224): The size of the input image. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input image. kernel_size (`int`, *optional*, defaults to 3): The kernel size for the initial convolution layers of patch embedding. stride (`int`, *optional*, defaults to 2): The stride size for the initial convolution layers of patch embedding. padding (`int`, *optional*, defaults to 1): The padding size for the initial convolution layers of patch embedding. patch_size (`int`, *optional*, defaults to 16): The patch size for embeddings. hidden_sizes (`List[int]`, *optional*, defaults to `[128, 256, 384]`): Dimension of each of the encoder blocks. num_attention_heads (`List[int]`, *optional*, defaults to `[4, 8, 12]`): Number of attention heads for each attention layer in each block of the Transformer encoder. depths (`List[int]`, *optional*, defaults to `[4, 4, 4]`): The number of layers in each encoder block. key_dim (`List[int]`, *optional*, defaults to `[16, 16, 16]`): The size of key in each of the encoder blocks. drop_path_rate (`int`, *optional*, defaults to 0): The dropout probability for stochastic depths, used in the blocks of the Transformer encoder. mlp_ratios (`List[int]`, *optional*, defaults to `[2, 2, 2]`): Ratio of the size of the hidden layer compared to the size of the input layer of the Mix FFNs in the encoder blocks. attention_ratios (`List[int]`, *optional*, defaults to `[2, 2, 2]`): Ratio of the size of the output dimension compared to input dimension of attention layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Example: ```python >>> from transformers import LevitConfig, LevitModel >>> # Initializing a LeViT levit-128S style configuration >>> configuration = LevitConfig() >>> # Initializing a model (with random weights) from the levit-128S style configuration >>> model = LevitModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zlevitri rg{Gz?c stjf|||_||_||_||_||_||_||_| |_ | |_ | |_ ||_ | |_ | |_||_d| d|d| ddddgd| d|d| ddddgg|_dS)NZ Subsamplerrr r )super__init__ image_size num_channels kernel_sizestridepadding hidden_sizesnum_attention_headsdepthskey_dimdrop_path_rate patch_sizeattention_ratio mlp_ratioinitializer_rangeZdown_ops)selfrrrrrr rrrrrr"r!r#kwargs __class__l/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/levit/configuration_levit.pyr\s$zLevitConfig.__init__)__name__ __module__ __qualname____doc__Z model_typer __classcell__r(r(r&r)r #s"6r c@sJeZdZedZeeeee effdddZ ee dddZ dS)LevitOnnxConfigz1.11)returncCstddddddfgS)NZ pixel_valuesbatchrheightwidth)rr r rrr$r(r(r)inputsszLevitOnnxConfig.inputscCsdS)Ng-C6?r(r4r(r(r)atol_for_validationsz#LevitOnnxConfig.atol_for_validationN) r*r+r,rparseZtorch_onnx_minimum_versionpropertyrstrintr5floatr6r(r(r(r)r/s   r/N)r- collectionsrtypingr packagingrZconfiguration_utilsrZonnxrutilsr Z get_loggerr*loggerZ#LEVIT_PRETRAINED_CONFIG_ARCHIVE_MAPr r/r(r(r(r)s       a