sg dZddlZddlmZddlmZmZmZddlZddl Zddlm Z ddl m Z m Z mZddlmZdd lmZdd lmZdd lmZmZdd lmZmZmZmZmZmZmZm Z m!Z!dd l"m#Z#ddl$m%Z%er ddl&m'Z'm(Z(ndZ(dZ'ejRe*Z+dZ,dZ-gdZ.dZ/dZ0eGddeZ1eGddeZ2eGddeZ3Gdde jhZ5Gdd e jhZ6Gd!d"e jhZ7dGd#ejpd$e9d%e:d&ejpfd'Z;Gd(d)e jhZ<Gd*d+e jhZ=Gd,d-e jhZ>Gd.d/e jhZ?Gd0d1e jhZ@Gd2d3e jhZAGd4d5e jhZBGd6d7e jhZCGd8d9e jhZDGd:d;eZEdeFGd?d@eEZHedAeFGdBdCeEZIedDeFGdEdFeEe#ZJy)Hz9PyTorch Dilated Neighborhood Attention Transformer model.N) dataclass)OptionalTupleUnion)nn)BCEWithLogitsLossCrossEntropyLossMSELoss)ACT2FN)BackboneOutput)PreTrainedModel) find_pruneable_heads_and_indicesprune_linear_layer) ModelOutputOptionalDependencyNotAvailableadd_code_sample_docstringsadd_start_docstrings%add_start_docstrings_to_model_forwardis_natten_availableloggingreplace_return_docstringsrequires_backends) BackboneMixin) DinatConfig) natten2dav natten2dqkrpbctNrargskwargss [/var/www/html/venv/lib/python3.12/site-packages/transformers/models/dinat/modeling_dinat.pyrr1 ,..ctr r!r"s r%rr4r&r'rzshi-labs/dinat-mini-in1k-224)rr)iztabby, tabby catceZdZUdZdZej ed<dZe e ej dfed<dZ e e ej dfed<dZ e e ej dfed<y)DinatEncoderOutputa Dinat encoder's outputs, with potential hidden states and attentions. Args: last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Sequence of hidden-states at the output of the last layer of the model. 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 stage) 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 stage) 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. reshaped_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 stage) of shape `(batch_size, hidden_size, height, width)`. Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to include the spatial dimensions. Nlast_hidden_state. hidden_states attentionsreshaped_hidden_states) __name__ __module__ __qualname____doc__r,torch FloatTensor__annotations__r-rrr.r/r'r%r+r+Isx2,0u((/=AM8E%"3"3S"89:A:>Ju00#567>FJHU5+<+