^j jdZddlmZddlmZddlmZedeGdd eZd gZy ) zVideoMAE model configuration)strict)PreTrainedConfig)auto_docstringzMCG-NJU/videomae-base) checkpointceZdZUdZdZdZeeezeeefze d<dZ eeezeeefze d<dZ ee d<dZ ee d <d Z ee d <d Zee d <dZee d<dZee d<dZee d<dZee d<dZeeze d<dZeeze d<dZee d<dZee d<dZee d<dZee d<dZee d <d!Zee d"<d#Zee d$<d%Zee d&<dZ ee d'<y())VideoMAEConfigak num_frames (`int`, *optional*, defaults to 16): The number of frames in each video. tubelet_size (`int`, *optional*, defaults to 2): The number of tubelets. use_mean_pooling (`bool`, *optional*, defaults to `True`): Whether to mean pool the final hidden states instead of using the final hidden state of the [CLS] token. decoder_num_attention_heads (`int`, *optional*, defaults to 6): Number of attention heads for each attention layer in the decoder. decoder_hidden_size (`int`, *optional*, defaults to 384): Dimensionality of the decoder. decoder_num_hidden_layers (`int`, *optional*, defaults to 4): Number of hidden layers in the decoder. decoder_intermediate_size (`int`, *optional*, defaults to 1536): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the decoder. norm_pix_loss (`bool`, *optional*, defaults to `True`): Whether to normalize the target patch pixels. Example: ```python >>> from transformers import VideoMAEConfig, VideoMAEModel >>> # Initializing a VideoMAE videomae-base style configuration >>> configuration = VideoMAEConfig() >>> # Randomly initializing a model from the configuration >>> model = VideoMAEModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```videomae image_size patch_sizer num_channels num_frames tubelet_sizei hidden_size num_hidden_layersnum_attention_headsi intermediate_sizegelu hidden_actghidden_dropout_probattention_probs_dropout_probg{Gz?initializer_rangeg-q=layer_norm_epsTqkv_biasuse_mean_poolingdecoder_num_attention_headsidecoder_hidden_sizedecoder_num_hidden_layersidecoder_intermediate_size norm_pix_lossN)!__name__ __module__ __qualname____doc__ model_typer intlisttuple__annotations__rrrrrrrrrstrrfloatrrrrboolrr!r"r$r%r&~/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/videomae/configuration_videomae.pyr r s BJ47Jd3i%S/1746Jd3i%S/16L#JL#Ks!!!s!J'**03 %#+3#u#!NE!Hd!d!'((""%&s&%)s)M4r4r N) r*huggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__r3r4r5r:sH#.3#238%848v  r4