o ei_@sNdZddlmZddlmZddlmZeeZ GdddeeZ dgZ dS)zConvNeXT model configuration)BackboneConfigMixin)PreTrainedConfig)loggingcs@eZdZdZdZ          dfd d ZZS)ConvNextConfiga This is the configuration class to store the configuration of a [`ConvNextModel`]. It is used to instantiate an ConvNeXT 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 ConvNeXT [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-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: num_channels (`int`, *optional*, defaults to 3): The number of input channels. patch_size (`int`, *optional*, defaults to 4): Patch size to use in the patch embedding layer. num_stages (`int`, *optional*, defaults to 4): The number of stages in the model. hidden_sizes (`list[int]`, *optional*, defaults to [96, 192, 384, 768]): Dimensionality (hidden size) at each stage. depths (`list[int]`, *optional*, defaults to [3, 3, 9, 3]): Depth (number of blocks) for each stage. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in each block. 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 1e-6): The initial value for the layer scale. drop_path_rate (`float`, *optional*, defaults to 0.0): The drop rate for stochastic depth. 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. Must be in the same order as defined in the `stage_names` attribute. 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. Must be in the same order as defined in the `stage_names` attribute. Example: ```python >>> from transformers import ConvNextConfig, ConvNextModel >>> # Initializing a ConvNext convnext-tiny-224 style configuration >>> configuration = ConvNextConfig() >>> # Initializing a model (with random weights) from the convnext-tiny-224 style configuration >>> model = ConvNextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```convnextrNgelu{Gz?-q=ư>c stjdi|||_||_||_|durgdn||_|dur%gdn||_||_||_||_ | |_ | |_ | |_ dgddt dt|jdD|_|j| | ddS) N)`ii)rr rstemcSsg|]}d|qS)stage).0idxrrq/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/convnext/configuration_convnext.py qsz+ConvNextConfig.__init__..) out_indices out_featuresr)super__init__ num_channels patch_size num_stages hidden_sizesdepths hidden_actinitializer_rangelayer_norm_epslayer_scale_init_valuedrop_path_rate image_sizerangelen stage_names"set_output_features_output_indices)selfrrrr r!r"r#r$r%r&r'rrkwargs __class__rrrSs&zConvNextConfig.__init__) rrrNNrr r r r r NN)__name__ __module__ __qualname____doc__ model_typer __classcell__rrr.rrs"8rN) r3backbone_utilsrconfiguration_utilsrutilsr get_loggerr0loggerr__all__rrrrs     ]