U ,-e@sTdZddlmZddlmZddlmZmZee Z ddiZ GdddeeZ d S) z? Dilated Neighborhood Attention Transformer model configuration)PretrainedConfig)logging)BackboneConfigMixin*get_aligned_output_features_output_indiceszshi-labs/dinat-mini-in1k-224zLhttps://huggingface.co/shi-labs/dinat-mini-in1k-224/resolve/main/config.jsoncseZdZdZdZdddZdddddd d gd dd d gddd dgddddgdd dd dd gdddddggdddddddddddffdd ZZS) DinatConfiga This is the configuration class to store the configuration of a [`DinatModel`]. It is used to instantiate a Dinat 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 Dinat [shi-labs/dinat-mini-in1k-224](https://huggingface.co/shi-labs/dinat-mini-in1k-224) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: patch_size (`int`, *optional*, defaults to 4): The size (resolution) of each patch. NOTE: Only patch size of 4 is supported at the moment. num_channels (`int`, *optional*, defaults to 3): The number of input channels. embed_dim (`int`, *optional*, defaults to 64): Dimensionality of patch embedding. depths (`List[int]`, *optional*, defaults to `[2, 2, 6, 2]`): Number of layers in each level of the encoder. num_heads (`List[int]`, *optional*, defaults to `[3, 6, 12, 24]`): Number of attention heads in each layer of the Transformer encoder. kernel_size (`int`, *optional*, defaults to 7): Neighborhood Attention kernel size. dilations (`List[List[int]]`, *optional*, defaults to `[[1, 8, 1], [1, 4, 1, 4], [1, 2, 1, 2, 1, 2], [1, 1, 1, 1, 1]]`): Dilation value of each NA layer in the Transformer encoder. mlp_ratio (`float`, *optional*, defaults to 3.0): Ratio of MLP hidden dimensionality to embedding dimensionality. qkv_bias (`bool`, *optional*, defaults to `True`): Whether or not a learnable bias should be added to the queries, keys and values. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings and encoder. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. drop_path_rate (`float`, *optional*, defaults to 0.1): Stochastic depth rate. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. 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-12): The epsilon used by the layer normalization layers. layer_scale_init_value (`float`, *optional*, defaults to 0.0): The initial value for the layer scale. Disabled if <=0. out_features (`List[str]`, *optional*): If used as backbone, list of features to output. Can be any of `"stem"`, `"stage1"`, `"stage2"`, etc. (depending on how many stages the model has). If unset and `out_indices` is set, will default to the corresponding stages. If unset and `out_indices` is unset, will default to the last stage. out_indices (`List[int]`, *optional*): If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). If unset and `out_features` is set, will default to the corresponding stages. If unset and `out_features` is unset, will default to the last stage. Example: ```python >>> from transformers import DinatConfig, DinatModel >>> # Initializing a Dinat shi-labs/dinat-mini-in1k-224 style configuration >>> configuration = DinatConfig() >>> # Initializing a model (with random weights) from the shi-labs/dinat-mini-in1k-224 style configuration >>> model = DinatModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zdinat num_heads num_layers)Znum_attention_headsZnum_hidden_layersr@g@Tgg?Zgelug{Gz?gh㈵>Nc stjf|||_||_||_||_t||_||_||_ ||_ ||_ | |_ | |_ | |_| |_| |_||_||_t|dt|d|_||_dgddtdt|dD|_t|||jd\|_|_dS)Nr rstemcSsg|]}d|qS)Zstage).0idxrrn/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/dinat/configuration_dinat.py sz(DinatConfig.__init__..) out_features out_indices stage_names)super__init__ patch_size num_channels embed_dimdepthslenrr kernel_size dilations mlp_ratioqkv_biashidden_dropout_probattention_probs_dropout_probdrop_path_rate hidden_actlayer_norm_epsinitializer_rangeintZ hidden_sizelayer_scale_init_valuerangerrZ _out_featuresZ _out_indices)selfrrrr rr"r#r$r%r&r'r(r)r+r*r-rrkwargs __class__rrrhs2 $zDinatConfig.__init__)__name__ __module__ __qualname____doc__Z model_typeZ attribute_mapr __classcell__rrr1rrs0B  .rN) r6Zconfiguration_utilsrutilsrZutils.backbone_utilsrrZ get_loggerr3loggerZ#DINAT_PRETRAINED_CONFIG_ARCHIVE_MAPrrrrrs