T^(h`dZddlmZddlmZej eZGddeZdgZ y)zViViT model configuration)PretrainedConfig)loggingcHeZdZdZdZddgdddddd d d d d d dffd ZxZS) VivitConfiga This is the configuration class to store the configuration of a [`VivitModel`]. It is used to instantiate a ViViT 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 ViViT [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) 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 (resolution) of each image. num_frames (`int`, *optional*, defaults to 32): The number of frames in each video. tubelet_size (`List[int]`, *optional*, defaults to `[2, 16, 16]`): The size (resolution) of each tubelet. num_channels (`int`, *optional*, defaults to 3): The number of input channels. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu_fast"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"`, `"gelu_fast"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. 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-06): 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. Example: ```python >>> from transformers import VivitConfig, VivitModel >>> # Initializing a ViViT google/vivit-b-16x2-kinetics400 style configuration >>> configuration = VivitConfig() >>> # Initializing a model (with random weights) from the google/vivit-b-16x2-kinetics400 style configuration >>> model = VivitModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```vivit )r ri i gelu_fastgg{Gz?gư>Tc ||_||_||_||_| |_| |_| |_| |_| |_||_ ||_ ||_ ||_ ||_ t|<di|y)N) hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size num_frames tubelet_size num_channelsqkv_biassuper__init__)selfrrrrrrrrrrrrrrkwargs __class__s k/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/vivit/configuration_vivit.pyrzVivitConfig.__init__Rs$'!2#6 !2$#6 ,H)!2,$$((   "6")__name__ __module__ __qualname____doc__ model_typer __classcell__)r"s@r#rrsF5 nJ %("#"#r$rN) r(configuration_utilsrutilsr get_loggerr%loggerr__all__rr$r#r0s= 3   H %\#"\#~ /r$