sgdZddlZddlZddlmZddlmZddlm Z m Z m Z m Z ddl ZddlZddlZddlmZddlmZmZmZdd lmZdd lmZmZdd lmZdd lmZmZdd l m!Z!m"Z"m#Z#m$Z$m%Z%ddl&m'Z'm(Z(ddl)m*Z*e$jVe,Z-dZ.dZ/eGdde!Z0eGdde!Z1dZ2GddejfZ4GddejfZ5GddejfZ6Gdde6Z7Gd d!ejfZ8Gd"d#ejfZ9Gd$d%e9Z:Gd&d'ejfZ;Gd(d)ejfZGd-d.ejfZ?Gd/d0eZ@d1ZAd2ZBe"d3eAGd4d5e@ZCGd6d7ejfZDe"d8eAGd9d:e@ZEe"d;eAGd<d=e@ZFy)>z,PyTorch VideoMAE (masked autoencoder) model.N)deepcopy) dataclass)OptionalSetTupleUnion)nn)BCEWithLogitsLossCrossEntropyLossMSELoss)ACT2FN)BaseModelOutputImageClassifierOutput)PreTrainedModel) 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-baseceZdZUdZdZej ed<dZe e ej ed<dZ e e ej ed<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__rtorch FloatTensor__annotations__r rrr!a/var/www/html/venv/lib/python3.12/site-packages/transformers/models/videomae/modeling_videomae.pyrr2sM !%FE  $8