T^(hHdZddlZddlmZddlmZddlmZm Z m Z m Z m Z ddl ZddlZddlZddlmZddlmZmZmZdd lmZdd lmZmZdd lmZmZdd lmZm Z dd l!m"Z"m#Z#m$Z$m%Z%m&Z&ddl'm(Z(m)Z)ddl*m+Z+e%jXe-Z.dZ/dZ0eGdde"Z1eGdde"Z2dZ3GddejhZ5GddejhZ6 dBdejhdejndejndejnd e ejnd!e8d"e8fd#Z9Gd$d%ejhZ:Gd&d'ejhZ;Gd(d)ejhZ<Gd*d+ejhZ=Gd,d-ejhZ>Gd.d/ejhZ?Gd0d1ejhZ@Gd2d3eZAd4ZBd5ZCe#d6eBGd7d8eAZDGd9d:ejhZEe#d;eBGd<d=eAZFe#d>eBGd?d@eAZGgdAZHy)Cz,PyTorch VideoMAE (masked autoencoder) model.N)deepcopy) dataclass)CallableOptionalSetTupleUnion)nn)BCEWithLogitsLossCrossEntropyLossMSELoss)ACT2FN)BaseModelOutputImageClassifierOutput)ALL_ATTENTION_FUNCTIONSPreTrainedModel) find_pruneable_heads_and_indicesprune_linear_layer) ModelOutputadd_start_docstrings%add_start_docstrings_to_model_forwardloggingreplace_return_docstrings)IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STD)VideoMAEConfigrzMCG-NJU/videomae-baseceZdZUdZdZeejed<dZ ee ejed<dZ ee ejed<y)VideoMAEDecoderOutputaO Class for VideoMAEDecoder's outputs, with potential hidden states and attentions. Args: logits (`torch.FloatTensor` of shape `(batch_size, patch_size ** 2 * num_channels)`): Pixel reconstruction logits. hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs. attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Nlogits hidden_states attentions) __name__ __module__ __qualname____doc__r!rtorch FloatTensor__annotations__r"rr#l/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/videomae/modeling_videomae.pyr r 1sR +/FHU&& '.8